Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5499 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.6442. Min Act: -0.1700
Data Index: 4664662 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.6129. Min Act: -0.1700
Data Index: 1998340 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5504. Min Act: -0.1700
Data Index: 4269888 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5504. Min Act: -0.1700
Data Index: 5699425 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5192. Min Act: -0.1700
Data Index: 7452374 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5192. Min Act: -0.1700
Data Index: 8232218 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5504. Min Act: -0.1700
Data Index: 8581848 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.5504. Min Act: -0.1700
Data Index: 3533626 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4879. Min Act: -0.1700
Data Index: 387071 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4879. Min Act: -0.1700
Data Index: 629404 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4879. Min Act: -0.1700
Data Index: 3023264 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4879. Min Act: -0.1700
Data Index: 8280538 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4567. Min Act: -0.1700
Data Index: 3385184 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4254. Min Act: -0.1700
Data Index: 3342471 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5499859 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.4567. Min Act: -0.1700
Data Index: 7283869 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.3942. Min Act: -0.1700
Data Index: 2370663 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8558959 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.3942. Min Act: -0.1700
Data Index: 2430920 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6442. Min Range: -6.6442
Max Act: 6.3942. Min Act: -0.1700
Data Index: 258040 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19