Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.4643. Min Act: -0.1700
Data Index: 2434290 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.3393. Min Act: -0.1700
Data Index: 3106334 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.3080. Min Act: -0.1700
Data Index: 2757474 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.2768. Min Act: -0.1700
Data Index: 6303550 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.2455. Min Act: -0.1700
Data Index: 7884695 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.2455. Min Act: -0.1700
Data Index: 6055175 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.2143. Min Act: -0.1700
Data Index: 8661395 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1830. Min Act: -0.1700
Data Index: 4570253 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.2143. Min Act: -0.1700
Data Index: 1061431 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1518. Min Act: -0.1700
Data Index: 1928654 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1518. Min Act: -0.1700
Data Index: 4141239 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1518. Min Act: -0.1700
Data Index: 5088571 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1205. Min Act: -0.1700
Data Index: 3774755 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0893. Min Act: -0.1700
Data Index: 880504 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.1205. Min Act: -0.1700
Data Index: 932390 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0893. Min Act: -0.1700
Data Index: 6972113 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0580. Min Act: -0.1700
Data Index: 8642358 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0893. Min Act: -0.1700
Data Index: 2524709 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0580. Min Act: -0.1700
Data Index: 4662102 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4643. Min Range: -7.4643
Max Act: 7.0893. Min Act: -0.1700
Data Index: 6628957 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19