Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.3027. Min Act: -0.1700
Data Index: 1089892 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.2402. Min Act: -0.1700
Data Index: 1114064 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.2090. Min Act: -0.1700
Data Index: 3389413 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1777. Min Act: -0.1700
Data Index: 4914572 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1777. Min Act: -0.1700
Data Index: 148532 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1777. Min Act: -0.1700
Data Index: 7577670 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1465. Min Act: -0.1700
Data Index: 4719758 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1465. Min Act: -0.1700
Data Index: 4538238 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1152. Min Act: -0.1700
Data Index: 803781 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1152. Min Act: -0.1700
Data Index: 4973437 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.1152. Min Act: -0.1700
Data Index: 6781304 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4538241 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0840. Min Act: -0.1700
Data Index: 1114063 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0527. Min Act: -0.1700
Data Index: 206795 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0840. Min Act: -0.1700
Data Index: 568252 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0527. Min Act: -0.1700
Data Index: 7473439 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0527. Min Act: -0.1700
Data Index: 770154 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0527. Min Act: -0.1700
Data Index: 1799366 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0215. Min Act: -0.1700
Data Index: 770166 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3027. Min Range: -5.3027
Max Act: 5.0215. Min Act: -0.1700
Data Index: 3975911 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19