Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2430 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3726. Min Act: -0.1700
Data Index: 1404506 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3414. Min Act: -0.1700
Data Index: 8679935 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1847657 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.4039. Min Act: -0.1700
Data Index: 6666029 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3726. Min Act: -0.1700
Data Index: 1512603 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5763648 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3101. Min Act: -0.1700
Data Index: 8064525 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.3414. Min Act: -0.1700
Data Index: 4340270 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.2789. Min Act: -0.1700
Data Index: 4513813 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1851. Min Act: -0.1700
Data Index: 6707362 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1539. Min Act: -0.1700
Data Index: 27213 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1226. Min Act: -0.1700
Data Index: 1657388 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1539. Min Act: -0.1700
Data Index: 2868613 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1226. Min Act: -0.1700
Data Index: 2456138 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.0914. Min Act: -0.1700
Data Index: 3376119 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1226. Min Act: -0.1700
Data Index: 1335092 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1226. Min Act: -0.1700
Data Index: 550470 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4282647 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.0914. Min Act: -0.1700
Data Index: 8235793 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4039. Min Range: -5.4039
Max Act: 5.1226. Min Act: -0.1700
Data Index: 4573451 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19