Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3299. Min Range: -7.3299
Max Act: 7.3299. Min Act: -0.1700
Data Index: 7169019 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3299. Min Range: -7.3299
Max Act: 7.2362. Min Act: -0.1700
Data Index: 4029928 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3299. Min Range: -7.3299
Max Act: 7.1112. Min Act: -0.1700
Data Index: 8181182 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3299. Min Range: -7.3299
Max Act: 7.0799. Min Act: -0.1700
Data Index: 7012010 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.9862. Min Act: -0.1700
Data Index: 3863784 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.8612. Min Act: -0.1700
Data Index: 1786906 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.7362. Min Act: -0.1700
Data Index: 5305598 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.7674. Min Act: -0.1700
Data Index: 6100742 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.6424. Min Act: -0.1700
Data Index: 294155 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.6112. Min Act: -0.1700
Data Index: 4492429 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.6112. Min Act: -0.1700
Data Index: 5063462 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1270105 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 7616450 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.4862. Min Act: -0.1700
Data Index: 710402 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 7441380 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.4549. Min Act: -0.1700
Data Index: 1425329 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.4549. Min Act: -0.1700
Data Index: 7594175 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.3924. Min Act: -0.1700
Data Index: 353307 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.4237. Min Act: -0.1700
Data Index: 4455263 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3299. Min Range: -7.3299
Max Act: 6.3924. Min Act: -0.1700
Data Index: 2104296 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19