Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2610 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.6915. Min Act: -0.1700
Data Index: 3916722 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.3478. Min Act: -0.1700
Data Index: 357339 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.1290. Min Act: -0.1700
Data Index: 3670871 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.1290. Min Act: -0.1700
Data Index: 1306295 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0978. Min Act: -0.1700
Data Index: 387318 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0978. Min Act: -0.1700
Data Index: 3474801 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0040. Min Act: -0.1700
Data Index: 4421296 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7753866 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9728. Min Act: -0.1700
Data Index: 1162664 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6915. Min Range: -7.6915
Max Act: 7.0040. Min Act: -0.1700
Data Index: 5016041 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9728. Min Act: -0.1700
Data Index: 8707389 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 7826282 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9415. Min Act: -0.1700
Data Index: 5976952 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9103. Min Act: -0.1700
Data Index: 6905296 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9103. Min Act: -0.1700
Data Index: 4205979 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.9103. Min Act: -0.1700
Data Index: 1998362 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.8790. Min Act: -0.1700
Data Index: 6811998 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.8478. Min Act: -0.1700
Data Index: 6698025 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.8478. Min Act: -0.1700
Data Index: 7354568 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6915. Min Range: -7.6915
Max Act: 6.8478. Min Act: -0.1700
Data Index: 8296977 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19