Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 114 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3613. Min Range: -8.3613
Max Act: 8.3613. Min Act: -0.1700
Data Index: 8098371 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3613. Min Range: -8.3613
Max Act: 8.2363. Min Act: -0.1700
Data Index: 3581824 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3613. Min Range: -8.3613
Max Act: 8.1113. Min Act: -0.1700
Data Index: 6259479 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3613. Min Range: -8.3613
Max Act: 8.0488. Min Act: -0.1700
Data Index: 1184474 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 8718389 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9863. Min Act: -0.1700
Data Index: 886732 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9863. Min Act: -0.1700
Data Index: 8723721 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9863. Min Act: -0.1700
Data Index: 7273925 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3613. Min Range: -8.3613
Max Act: 8.0488. Min Act: -0.1700
Data Index: 3715745 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 2207682 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 5586201 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 5009708 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 2079548 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 4095399 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.8613. Min Act: -0.1700
Data Index: 1173300 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.8613. Min Act: -0.1700
Data Index: 7970128 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.8613. Min Act: -0.1700
Data Index: 2787251 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.9238. Min Act: -0.1700
Data Index: 8352217 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.7988. Min Act: -0.1700
Data Index: 7601212 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3613. Min Range: -8.3613
Max Act: 7.7988. Min Act: -0.1700
Data Index: 6046293 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19