Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.7471. Min Act: -0.1700
Data Index: 201918 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.7471. Min Act: -0.1700
Data Index: 5400677 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.5908. Min Act: -0.1700
Data Index: 4742575 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.5596. Min Act: -0.1700
Data Index: 6832235 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.5596. Min Act: -0.1700
Data Index: 8340491 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.4033. Min Act: -0.1700
Data Index: 3848427 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.4033. Min Act: -0.1700
Data Index: 8342110 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3721. Min Act: -0.1700
Data Index: 4106103 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3408. Min Act: -0.1700
Data Index: 3396539 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3408. Min Act: -0.1700
Data Index: 3480959 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3096. Min Act: -0.1700
Data Index: 4758212 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3096. Min Act: -0.1700
Data Index: 7276724 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.3096. Min Act: -0.1700
Data Index: 3258003 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.2158. Min Act: -0.1700
Data Index: 7276723 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.2158. Min Act: -0.1700
Data Index: 1798584 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.1846. Min Act: -0.1700
Data Index: 498432 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.2158. Min Act: -0.1700
Data Index: 8500900 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.1846. Min Act: -0.1700
Data Index: 587505 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.1533. Min Act: -0.1700
Data Index: 6658481 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7471. Min Range: -5.7471
Max Act: 5.1533. Min Act: -0.1700
Data Index: 379741 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19