Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.7972. Min Act: -0.1700
Data Index: 7985521 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.7493. Min Act: -0.1700
Data Index: 4939904 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.7334. Min Act: -0.1700
Data Index: 1276465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.7334. Min Act: -0.1700
Data Index: 3581185 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6854. Min Act: -0.1700
Data Index: 1949658 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6694. Min Act: -0.1700
Data Index: 2914141 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6694. Min Act: -0.1700
Data Index: 5115557 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6533. Min Act: -0.1700
Data Index: 6847004 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6694. Min Act: -0.1700
Data Index: 2798011 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6533. Min Act: -0.1700
Data Index: 1732358 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6854. Min Act: -0.1700
Data Index: 6797799 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6533. Min Act: -0.1700
Data Index: 2503247 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 2565324 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 8083359 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 494339 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 4737198 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 7375606 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6373. Min Act: -0.1700
Data Index: 7632986 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6051. Min Act: -0.1700
Data Index: 6634745 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7972. Min Range: -2.7972
Max Act: 2.6212. Min Act: -0.1700
Data Index: 2298807 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19