Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6331 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4263. Min Range: -7.4263
Max Act: 7.4263. Min Act: -0.1700
Data Index: 8180351 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4263. Min Range: -7.4263
Max Act: 7.1451. Min Act: -0.1700
Data Index: 1107151 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8951. Min Act: -0.1700
Data Index: 8672443 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8951. Min Act: -0.1700
Data Index: 6720477 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8638. Min Act: -0.1700
Data Index: 4551901 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8638. Min Act: -0.1700
Data Index: 4734419 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8326. Min Act: -0.1700
Data Index: 6826326 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.8013. Min Act: -0.1700
Data Index: 3798033 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.7701. Min Act: -0.1700
Data Index: 793933 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.7701. Min Act: -0.1700
Data Index: 7264144 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.7076. Min Act: -0.1700
Data Index: 3902606 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6330017 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6763. Min Act: -0.1700
Data Index: 1855528 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6763. Min Act: -0.1700
Data Index: 6889792 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6451. Min Act: -0.1700
Data Index: 4911794 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6451. Min Act: -0.1700
Data Index: 2401943 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3884149 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6138. Min Act: -0.1700
Data Index: 8354270 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.6138. Min Act: -0.1700
Data Index: 1905283 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4263. Min Range: -7.4263
Max Act: 6.5826. Min Act: -0.1700
Data Index: 3713256 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19