Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7266. Min Act: -0.1700
Data Index: 6631292 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7266. Min Act: -0.1700
Data Index: 7788466 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7106. Min Act: -0.1700
Data Index: 3945482 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7106. Min Act: -0.1700
Data Index: 3428107 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6946. Min Act: -0.1700
Data Index: 796164 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6625. Min Act: -0.1700
Data Index: 7435813 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6625. Min Act: -0.1700
Data Index: 6076714 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6304. Min Act: -0.1700
Data Index: 580744 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6465. Min Act: -0.1700
Data Index: 7788465 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6304. Min Act: -0.1700
Data Index: 238792 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6143. Min Act: -0.1700
Data Index: 2403100 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6143. Min Act: -0.1700
Data Index: 5318519 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6143. Min Act: -0.1700
Data Index: 7882419 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 33130 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 4096555 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 4924150 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 2271957 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 3389412 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 5994782 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 567885 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19