Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5397 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0215. Min Range: -7.0215
Max Act: 7.0215. Min Act: -0.1700
Data Index: 6542334 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.9590. Min Act: -0.1700
Data Index: 1025331 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.9277. Min Act: -0.1700
Data Index: 7121570 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.8652. Min Act: -0.1700
Data Index: 4148013 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.7402. Min Act: -0.1700
Data Index: 7365860 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.7402. Min Act: -0.1700
Data Index: 496793 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.7402. Min Act: -0.1700
Data Index: 4341802 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.7402. Min Act: -0.1700
Data Index: 3107069 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.6777. Min Act: -0.1700
Data Index: 4968068 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.6777. Min Act: -0.1700
Data Index: 3056910 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.6465. Min Act: -0.1700
Data Index: 3181933 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.6465. Min Act: -0.1700
Data Index: 3747905 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.6152. Min Act: -0.1700
Data Index: 6495483 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2429459 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5840. Min Act: -0.1700
Data Index: 7359240 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5527. Min Act: -0.1700
Data Index: 6338696 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5527. Min Act: -0.1700
Data Index: 7527948 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5527. Min Act: -0.1700
Data Index: 4004596 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5215. Min Act: -0.1700
Data Index: 7220714 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0215. Min Range: -7.0215
Max Act: 6.5215. Min Act: -0.1700
Data Index: 6601792 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19