Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1397. Min Range: -6.1397
Max Act: 6.1397. Min Act: -0.1700
Data Index: 2951098 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1397. Min Range: -6.1397
Max Act: 6.0147. Min Act: -0.1700
Data Index: 4560410 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9834. Min Act: -0.1700
Data Index: 6563733 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9522. Min Act: -0.1700
Data Index: 433007 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9522. Min Act: -0.1700
Data Index: 8579168 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9522. Min Act: -0.1700
Data Index: 2471711 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9209. Min Act: -0.1700
Data Index: 3202030 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.9209. Min Act: -0.1700
Data Index: 8747790 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8897. Min Act: -0.1700
Data Index: 3619735 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8897. Min Act: -0.1700
Data Index: 7375839 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8584. Min Act: -0.1700
Data Index: 5197311 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1754553 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8897. Min Act: -0.1700
Data Index: 8229702 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8897. Min Act: -0.1700
Data Index: 8365584 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8584. Min Act: -0.1700
Data Index: 405201 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8584. Min Act: -0.1700
Data Index: 4504295 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8584. Min Act: -0.1700
Data Index: 1420711 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8272. Min Act: -0.1700
Data Index: 729936 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8272. Min Act: -0.1700
Data Index: 3072621 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1397. Min Range: -6.1397
Max Act: 5.8272. Min Act: -0.1700
Data Index: 7365432 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19