Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 424 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3529. Min Range: -6.3529
Max Act: 6.3529. Min Act: -0.1700
Data Index: 661233 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3529. Min Range: -6.3529
Max Act: 6.2592. Min Act: -0.1700
Data Index: 3805469 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3529. Min Range: -6.3529
Max Act: 6.2279. Min Act: -0.1700
Data Index: 470071 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3529. Min Range: -6.3529
Max Act: 6.1967. Min Act: -0.1700
Data Index: 6233231 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3529. Min Range: -6.3529
Max Act: 6.1342. Min Act: -0.1700
Data Index: 6299802 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.9154. Min Act: -0.1700
Data Index: 6682014 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.9154. Min Act: -0.1700
Data Index: 4697723 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.9154. Min Act: -0.1700
Data Index: 1859656 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.9154. Min Act: -0.1700
Data Index: 7255546 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.9154. Min Act: -0.1700
Data Index: 1207365 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8842. Min Act: -0.1700
Data Index: 6435486 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8529. Min Act: -0.1700
Data Index: 3319099 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8529. Min Act: -0.1700
Data Index: 2302420 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8529. Min Act: -0.1700
Data Index: 8451458 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8217. Min Act: -0.1700
Data Index: 913291 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8217. Min Act: -0.1700
Data Index: 5859446 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8217. Min Act: -0.1700
Data Index: 1700825 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.8217. Min Act: -0.1700
Data Index: 939389 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.7904. Min Act: -0.1700
Data Index: 7827318 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3529. Min Range: -6.3529
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1595149 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19