Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.3394. Min Act: -0.1700
Data Index: 7971892 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.2769. Min Act: -0.1700
Data Index: 7449895 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.2769. Min Act: -0.1700
Data Index: 5642149 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.1207. Min Act: -0.1700
Data Index: 3859200 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7788613 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3394. Min Range: -6.3394
Max Act: 6.0269. Min Act: -0.1700
Data Index: 8117954 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9957. Min Act: -0.1700
Data Index: 5343249 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9957. Min Act: -0.1700
Data Index: 3156131 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9644. Min Act: -0.1700
Data Index: 2205820 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9644. Min Act: -0.1700
Data Index: 3777694 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9644. Min Act: -0.1700
Data Index: 7748474 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9332. Min Act: -0.1700
Data Index: 237094 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6436152 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9332. Min Act: -0.1700
Data Index: 7409979 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9332. Min Act: -0.1700
Data Index: 3859202 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9019. Min Act: -0.1700
Data Index: 1479704 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7699534 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9019. Min Act: -0.1700
Data Index: 1762210 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5532248 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3394. Min Range: -6.3394
Max Act: 5.9019. Min Act: -0.1700
Data Index: 4862537 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19