Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.3980. Min Act: -0.1700
Data Index: 6463817 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.3355. Min Act: -0.1700
Data Index: 8280402 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.3355. Min Act: -0.1700
Data Index: 6049860 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.2417. Min Act: -0.1700
Data Index: 3204932 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.2105. Min Act: -0.1700
Data Index: 1657852 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.2105. Min Act: -0.1700
Data Index: 2007726 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.2105. Min Act: -0.1700
Data Index: 3598410 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1792. Min Act: -0.1700
Data Index: 8460984 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.2105. Min Act: -0.1700
Data Index: 4282533 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 6169739 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1480. Min Act: -0.1700
Data Index: 4735395 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1480. Min Act: -0.1700
Data Index: 523073 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 4381666 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 2867943 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 7764272 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3198235 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 8244938 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 5681821 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.1167. Min Act: -0.1700
Data Index: 7449792 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3980. Min Range: -5.3980
Max Act: 5.0855. Min Act: -0.1700
Data Index: 147178 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19