Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4307. Min Range: -9.4307
Max Act: 9.4307. Min Act: -0.1700
Data Index: 88904 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4307. Min Range: -9.4307
Max Act: 9.3057. Min Act: -0.1700
Data Index: 1610850 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4307. Min Range: -9.4307
Max Act: 9.1182. Min Act: -0.1700
Data Index: 26366 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.9932. Min Act: -0.1700
Data Index: 88905 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.9307. Min Act: -0.1700
Data Index: 656214 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.8369. Min Act: -0.1700
Data Index: 88903 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.6807. Min Act: -0.1700
Data Index: 8198581 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.5869. Min Act: -0.1700
Data Index: 8198582 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.5244. Min Act: -0.1700
Data Index: 656218 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.4619. Min Act: -0.1700
Data Index: 4076417 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.3994. Min Act: -0.1700
Data Index: 1287402 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.4307. Min Act: -0.1700
Data Index: 4076422 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.4307. Min Act: -0.1700
Data Index: 1208386 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.3369. Min Act: -0.1700
Data Index: 2300281 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.3057. Min Act: -0.1700
Data Index: 4076412 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.2744. Min Act: -0.1700
Data Index: 656221 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.2432. Min Act: -0.1700
Data Index: 4084881 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.2432. Min Act: -0.1700
Data Index: 1287399 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.2119. Min Act: -0.1700
Data Index: 5568759 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4307. Min Range: -9.4307
Max Act: 8.2119. Min Act: -0.1700
Data Index: 1208381 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19