Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.4214. Min Act: -0.1700
Data Index: 7060907 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.3744. Min Act: -0.1700
Data Index: 3433088 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.3117. Min Act: -0.1700
Data Index: 2929657 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.3273. Min Act: -0.1700
Data Index: 1002234 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.3117. Min Act: -0.1700
Data Index: 1575890 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2960. Min Act: -0.1700
Data Index: 4752995 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2645. Min Act: -0.1700
Data Index: 3460022 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2488. Min Act: -0.1700
Data Index: 1877003 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2803. Min Act: -0.1700
Data Index: 6626675 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2331. Min Act: -0.1700
Data Index: 1487530 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 6361379 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 146044 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 4062806 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 7817588 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 8139392 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2174. Min Act: -0.1700
Data Index: 3830768 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2017. Min Act: -0.1700
Data Index: 191239 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2017. Min Act: -0.1700
Data Index: 5526353 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2017. Min Act: -0.1700
Data Index: 2246137 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4214. Min Range: -3.4214
Max Act: 3.2017. Min Act: -0.1700
Data Index: 4629028 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19