Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4545 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.2916. Min Act: -0.1700
Data Index: 4592338 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.2916. Min Act: -0.1700
Data Index: 5604521 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.2604. Min Act: -0.1700
Data Index: 5594576 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.2916. Min Act: -0.1700
Data Index: 2740355 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 2140919 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 4507404 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 709253 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 5564962 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 5192574 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1979. Min Act: -0.1700
Data Index: 4013229 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1666. Min Act: -0.1700
Data Index: 8821383 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1666. Min Act: -0.1700
Data Index: 5896772 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 6562924 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 708564 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 4125707 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 6428809 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 7875370 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 2100310 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1354. Min Act: -0.1700
Data Index: 3739761 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2916. Min Range: -5.2916
Max Act: 5.1041. Min Act: -0.1700
Data Index: 628855 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19