Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.9950. Min Act: -0.1700
Data Index: 8589961 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.9950. Min Act: -0.1700
Data Index: 5188561 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.7450. Min Act: -0.1700
Data Index: 7513899 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.6200. Min Act: -0.1700
Data Index: 4122231 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.6200. Min Act: -0.1700
Data Index: 5527959 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.4950. Min Act: -0.1700
Data Index: 1498077 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.4950. Min Act: -0.1700
Data Index: 8347410 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 4220076 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.4950. Min Act: -0.1700
Data Index: 3346836 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 6079331 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 893030 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 2169666 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 5096212 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 3806503 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.2450. Min Act: -0.1700
Data Index: 6053628 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.2450. Min Act: -0.1700
Data Index: 917213 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.2450. Min Act: -0.1700
Data Index: 7596677 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.2450. Min Act: -0.1700
Data Index: 5701014 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.3700. Min Act: -0.1700
Data Index: 1147468 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 23.9950. Min Range: -23.9950
Max Act: 23.2450. Min Act: -0.1700
Data Index: 2926881 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19