Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0156. Min Range: -6.0156
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6128951 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.9531. Min Act: -0.1700
Data Index: 7617792 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.9219. Min Act: -0.1700
Data Index: 1109234 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.8281. Min Act: -0.1700
Data Index: 1825089 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7656. Min Act: -0.1700
Data Index: 6097361 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7656. Min Act: -0.1700
Data Index: 7560587 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7344. Min Act: -0.1700
Data Index: 5911563 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7344. Min Act: -0.1700
Data Index: 6580180 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7031. Min Act: -0.1700
Data Index: 5641331 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7031. Min Act: -0.1700
Data Index: 347019 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.7031. Min Act: -0.1700
Data Index: 5848811 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6719. Min Act: -0.1700
Data Index: 4323075 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1565074 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1143067 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1340726 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 6376525 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 119571 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1699
Data Index: 7844180 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6719. Min Act: -0.1700
Data Index: 466748 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0156. Min Range: -6.0156
Max Act: 5.6406. Min Act: -0.1700
Data Index: 844365 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19