Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1161. Min Range: -7.1161
Max Act: 7.1161. Min Act: -0.1699
Data Index: 1340341 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1161. Min Range: -7.1161
Max Act: 7.0848. Min Act: -0.1700
Data Index: 1530601 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1161. Min Range: -7.1161
Max Act: 7.0536. Min Act: -0.1699
Data Index: 4436871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1161. Min Range: -7.1161
Max Act: 7.0223. Min Act: -0.1700
Data Index: 3935179 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.8973. Min Act: -0.1700
Data Index: 1025074 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.8661. Min Act: -0.1700
Data Index: 1472794 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.8973. Min Act: -0.1700
Data Index: 8570186 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.8661. Min Act: -0.1700
Data Index: 1603777 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.8348. Min Act: -0.1700
Data Index: 7516810 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7723. Min Act: -0.1700
Data Index: 3649692 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7723. Min Act: -0.1700
Data Index: 1059325 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7723. Min Act: -0.1700
Data Index: 4854864 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7098. Min Act: -0.1700
Data Index: 4067031 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7098. Min Act: -0.1700
Data Index: 2219866 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.6786. Min Act: -0.1700
Data Index: 8005917 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.6786. Min Act: -0.1700
Data Index: 7495771 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.7098. Min Act: -0.1700
Data Index: 6309676 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.6473. Min Act: -0.1700
Data Index: 3347695 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.6473. Min Act: -0.1696
Data Index: 2094070 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1161. Min Range: -7.1161
Max Act: 6.6473. Min Act: -0.1699
Data Index: 2479112 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19