Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.5969. Min Act: -0.1700
Data Index: 7166441 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.4719. Min Act: -0.1700
Data Index: 1474399 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.4094. Min Act: -0.1700
Data Index: 5264233 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.3781. Min Act: -0.1700
Data Index: 7320672 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.3469. Min Act: -0.1700
Data Index: 5663585 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.3469. Min Act: -0.1700
Data Index: 4041366 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.2531. Min Act: -0.1700
Data Index: 4729753 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.2531. Min Act: -0.1700
Data Index: 4320802 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.2219. Min Act: -0.1700
Data Index: 4274044 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.2219. Min Act: -0.1700
Data Index: 1889887 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1906. Min Act: -0.1700
Data Index: 372919 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1594. Min Act: -0.1700
Data Index: 8470260 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1281. Min Act: -0.1700
Data Index: 3024287 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1281. Min Act: -0.1700
Data Index: 3114601 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1594. Min Act: -0.1700
Data Index: 3199516 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1281. Min Act: -0.1700
Data Index: 2888017 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.0969. Min Act: -0.1700
Data Index: 7821792 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1281. Min Act: -0.1700
Data Index: 1011900 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.0969. Min Act: -0.1700
Data Index: 6908273 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5969. Min Range: -6.5969
Max Act: 6.1594. Min Act: -0.1700
Data Index: 4013142 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19