Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.3254. Min Act: -0.1700
Data Index: 3704514 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2941. Min Act: -0.1700
Data Index: 520909 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2629. Min Act: -0.1700
Data Index: 5716679 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2941. Min Act: -0.1700
Data Index: 4668314 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2316. Min Act: -0.1700
Data Index: 156944 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2316. Min Act: -0.1700
Data Index: 8335031 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.2004. Min Act: -0.1700
Data Index: 5831586 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1691. Min Act: -0.1700
Data Index: 1156540 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1379. Min Act: -0.1700
Data Index: 1921093 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1379. Min Act: -0.1700
Data Index: 206615 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1066. Min Act: -0.1700
Data Index: 5172220 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1379. Min Act: -0.1700
Data Index: 8103699 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.1066. Min Act: -0.1700
Data Index: 3578148 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0754. Min Act: -0.1700
Data Index: 5700714 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0754. Min Act: -0.1700
Data Index: 8403155 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0441. Min Act: -0.1700
Data Index: 4427290 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0441. Min Act: -0.1700
Data Index: 2629414 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0441. Min Act: -0.1700
Data Index: 1007145 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0441. Min Act: -0.1700
Data Index: 134192 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3254. Min Range: -6.3254
Max Act: 6.0441. Min Act: -0.1700
Data Index: 520925 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19