Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4316 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4679. Min Range: -9.4679
Max Act: 9.4679. Min Act: -0.1700
Data Index: 1561643 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4679. Min Range: -9.4679
Max Act: 9.0929. Min Act: -0.1700
Data Index: 4131299 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4679. Min Range: -9.4679
Max Act: 9.0929. Min Act: -0.1700
Data Index: 2323429 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.9054. Min Act: -0.1700
Data Index: 5431290 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.5929. Min Act: -0.1700
Data Index: 5761188 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.4679. Min Act: -0.1700
Data Index: 7008669 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.5304. Min Act: -0.1700
Data Index: 6061343 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.5304. Min Act: -0.1700
Data Index: 7822942 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.4679. Min Act: -0.1700
Data Index: 1319374 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 626347 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.4054. Min Act: -0.1700
Data Index: 3310887 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 5424125 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 537044 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 7781229 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 4877948 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.2804. Min Act: -0.1700
Data Index: 7916198 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.3429. Min Act: -0.1700
Data Index: 130013 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.2804. Min Act: -0.1700
Data Index: 6051794 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.2804. Min Act: -0.1700
Data Index: 2154974 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4679. Min Range: -9.4679
Max Act: 8.0929. Min Act: -0.1700
Data Index: 2762198 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19