Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.6610. Min Act: -0.1700
Data Index: 342014 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.4735. Min Act: -0.1700
Data Index: 6879721 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.3797. Min Act: -0.1700
Data Index: 3079465 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.3172. Min Act: -0.1700
Data Index: 3475031 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.3172. Min Act: -0.1700
Data Index: 1759103 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.2547. Min Act: -0.1700
Data Index: 4735628 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.2235. Min Act: -0.1700
Data Index: 2986666 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.2235. Min Act: -0.1700
Data Index: 8111193 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.1922. Min Act: -0.1700
Data Index: 3593110 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.1922. Min Act: -0.1700
Data Index: 1115331 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.1610. Min Act: -0.1700
Data Index: 3673741 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.1297. Min Act: -0.1700
Data Index: 8123427 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.1297. Min Act: -0.1700
Data Index: 8726712 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 2406429 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0360. Min Act: -0.1700
Data Index: 1525189 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 4136739 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 8118497 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 12944 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0360. Min Act: -0.1700
Data Index: 4385475 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6610. Min Range: -5.6610
Max Act: 5.0360. Min Act: -0.1700
Data Index: 4488162 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19