Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.3186. Min Act: -0.1700
Data Index: 4774366 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2874. Min Act: -0.1700
Data Index: 6342742 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2561. Min Act: -0.1700
Data Index: 4514238 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2561. Min Act: -0.1700
Data Index: 1744779 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2249. Min Act: -0.1700
Data Index: 1600063 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2249. Min Act: -0.1700
Data Index: 4444245 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2249. Min Act: -0.1700
Data Index: 1972782 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.2249. Min Act: -0.1700
Data Index: 6256288 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1936. Min Act: -0.1700
Data Index: 3913905 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1624. Min Act: -0.1700
Data Index: 753642 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1624. Min Act: -0.1700
Data Index: 3327907 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1624. Min Act: -0.1700
Data Index: 754374 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1624. Min Act: -0.1700
Data Index: 4755104 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1311. Min Act: -0.1700
Data Index: 7527017 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.1311. Min Act: -0.1700
Data Index: 1646067 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.0999. Min Act: -0.1700
Data Index: 4301082 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.0686. Min Act: -0.1700
Data Index: 6155515 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.0999. Min Act: -0.1700
Data Index: 6047735 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.0999. Min Act: -0.1700
Data Index: 1784584 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3186. Min Range: -4.3186
Max Act: 4.0999. Min Act: -0.1700
Data Index: 5512590 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19