Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.8069. Min Act: -0.1700
Data Index: 5482854 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.8069. Min Act: -0.1700
Data Index: 1872016 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.6194. Min Act: -0.1700
Data Index: 7326426 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.5881. Min Act: -0.1700
Data Index: 5895176 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.5256. Min Act: -0.1700
Data Index: 5353061 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3694. Min Act: -0.1700
Data Index: 7749560 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3694. Min Act: -0.1700
Data Index: 6939406 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3381. Min Act: -0.1700
Data Index: 429149 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3069. Min Act: -0.1700
Data Index: 7093621 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3381. Min Act: -0.1700
Data Index: 1450438 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3069. Min Act: -0.1700
Data Index: 2025110 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.2756. Min Act: -0.1700
Data Index: 3749079 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.3069. Min Act: -0.1700
Data Index: 1859061 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.2131. Min Act: -0.1700
Data Index: 5813571 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.2131. Min Act: -0.1700
Data Index: 8198258 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.1819. Min Act: -0.1700
Data Index: 2313250 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.2131. Min Act: -0.1700
Data Index: 980188 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.1194. Min Act: -0.1700
Data Index: 2595336 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.1506. Min Act: -0.1700
Data Index: 2509092 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8069. Min Range: -7.8069
Max Act: 7.1194. Min Act: -0.1700
Data Index: 5877562 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19