Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1363 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1319. Min Range: -7.1319
Max Act: 7.1319. Min Act: -0.1700
Data Index: 4421424 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1319. Min Range: -7.1319
Max Act: 7.1007. Min Act: -0.1700
Data Index: 6045756 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1319. Min Range: -7.1319
Max Act: 7.0069. Min Act: -0.1700
Data Index: 3187812 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8819. Min Act: -0.1700
Data Index: 2931148 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8507. Min Act: -0.1700
Data Index: 7264965 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8194. Min Act: -0.1700
Data Index: 3973954 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8819. Min Act: -0.1700
Data Index: 4154826 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7882. Min Act: -0.1700
Data Index: 4326857 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8194. Min Act: -0.1700
Data Index: 4979454 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.8194. Min Act: -0.1700
Data Index: 1530789 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7569. Min Act: -0.1700
Data Index: 1012359 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7882. Min Act: -0.1700
Data Index: 8063419 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 2620822 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7569. Min Act: -0.1700
Data Index: 392244 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 1163333 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8048775 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7569. Min Act: -0.1700
Data Index: 4759201 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 5491019 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 97615 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1319. Min Range: -7.1319
Max Act: 6.7257. Min Act: -0.1700
Data Index: 6935841 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19