Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0552. Min Range: -3.0552
Max Act: 3.0552. Min Act: -0.1700
Data Index: 4230519 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.9604. Min Act: -0.1700
Data Index: 8391092 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.9604. Min Act: -0.1700
Data Index: 3756220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.9446. Min Act: -0.1700
Data Index: 2639524 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8970. Min Act: -0.1700
Data Index: 7612657 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8970. Min Act: -0.1700
Data Index: 2076235 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8812. Min Act: -0.1700
Data Index: 3758123 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5687622 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8653. Min Act: -0.1700
Data Index: 4230518 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8653. Min Act: -0.1700
Data Index: 344036 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8812. Min Act: -0.1700
Data Index: 6882917 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5629012 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8494. Min Act: -0.1700
Data Index: 2569321 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8494. Min Act: -0.1700
Data Index: 73201 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8494. Min Act: -0.1700
Data Index: 5345335 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8176. Min Act: -0.1700
Data Index: 4633016 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8017. Min Act: -0.1700
Data Index: 3095832 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.7858. Min Act: -0.1700
Data Index: 3639362 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.8017. Min Act: -0.1700
Data Index: 8641088 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0552. Min Range: -3.0552
Max Act: 2.7858. Min Act: -0.1700
Data Index: 5941074 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19