Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.9271. Min Act: -0.1700
Data Index: 8059114 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5410623 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4151420 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1698
Data Index: 5253187 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3107070 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6459. Min Act: -0.1700
Data Index: 1313350 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6459. Min Act: -0.1700
Data Index: 5570117 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6146. Min Act: -0.1700
Data Index: 8265404 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6146. Min Act: -0.1700
Data Index: 1375059 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6802340 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6077731 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5834. Min Act: -0.1700
Data Index: 2282787 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5834. Min Act: -0.1700
Data Index: 7414068 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5834. Min Act: -0.1700
Data Index: 7839152 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5521. Min Act: -0.1700
Data Index: 2312212 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5521. Min Act: -0.1700
Data Index: 3993767 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5209. Min Act: -0.1700
Data Index: 2299133 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5209. Min Act: -0.1700
Data Index: 4759307 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5209. Min Act: -0.1700
Data Index: 1282508 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.5209. Min Act: -0.1700
Data Index: 5416346 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19