Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0157. Min Range: -7.0157
Max Act: 7.0157. Min Act: -0.1700
Data Index: 4964230 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.9532. Min Act: -0.1700
Data Index: 6917521 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.9532. Min Act: -0.1700
Data Index: 2602411 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.8907. Min Act: -0.1700
Data Index: 6673921 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.7969. Min Act: -0.1700
Data Index: 4092417 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.7344. Min Act: -0.1700
Data Index: 8307616 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.6719. Min Act: -0.1700
Data Index: 4919882 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.6407. Min Act: -0.1700
Data Index: 4232975 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.6094. Min Act: -0.1700
Data Index: 5083922 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.6094. Min Act: -0.1700
Data Index: 2004856 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5782. Min Act: -0.1700
Data Index: 7733361 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5782. Min Act: -0.1700
Data Index: 2810414 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5782. Min Act: -0.1700
Data Index: 1403932 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5782. Min Act: -0.1700
Data Index: 8549224 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5782. Min Act: -0.1700
Data Index: 5236912 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5469. Min Act: -0.1700
Data Index: 136411 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5157. Min Act: -0.1700
Data Index: 5176136 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5469. Min Act: -0.1700
Data Index: 1318717 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.5157. Min Act: -0.1700
Data Index: 6445613 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0157. Min Range: -7.0157
Max Act: 6.4844. Min Act: -0.1700
Data Index: 5110230 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19