Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 6415978 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5885. Min Act: -0.1700
Data Index: 1424685 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 3534086 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5260. Min Act: -0.1700
Data Index: 3776242 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4635. Min Act: -0.1700
Data Index: 7270540 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 6020275 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4635. Min Act: -0.1700
Data Index: 8393810 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4830263 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 4232022 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 2257687 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3697. Min Act: -0.1700
Data Index: 8187537 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 7143314 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3385. Min Act: -0.1700
Data Index: 7928166 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 8402200 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 8452167 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5145736 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2760. Min Act: -0.1700
Data Index: 8488984 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2760. Min Act: -0.1700
Data Index: 4877255 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2760. Min Act: -0.1700
Data Index: 3227893 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2447. Min Act: -0.1700
Data Index: 6545529 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19