Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.7393. Min Act: -0.1700
Data Index: 2595741 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.6768. Min Act: -0.1700
Data Index: 5609873 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.6768. Min Act: -0.1700
Data Index: 1040051 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.6455. Min Act: -0.1700
Data Index: 8012706 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.6143. Min Act: -0.1700
Data Index: 4022148 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.5518. Min Act: -0.1700
Data Index: 379481 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4893. Min Act: -0.1700
Data Index: 489098 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.5205. Min Act: -0.1700
Data Index: 4406876 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.5205. Min Act: -0.1700
Data Index: 1369053 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4893. Min Act: -0.1700
Data Index: 5916301 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4893. Min Act: -0.1700
Data Index: 3076194 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4580. Min Act: -0.1700
Data Index: 4048527 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4580. Min Act: -0.1700
Data Index: 3177580 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4580. Min Act: -0.1700
Data Index: 1594400 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4268. Min Act: -0.1700
Data Index: 7997854 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4580. Min Act: -0.1700
Data Index: 5096903 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4268. Min Act: -0.1700
Data Index: 4982032 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.4268. Min Act: -0.1700
Data Index: 2766249 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.3955. Min Act: -0.1700
Data Index: 3728562 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7393. Min Range: -4.7393
Max Act: 4.3955. Min Act: -0.1700
Data Index: 240732 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19