Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4609 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5908104 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.8172. Min Act: -0.1700
Data Index: 3933698 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7860. Min Act: -0.1700
Data Index: 3682210 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7860. Min Act: -0.1700
Data Index: 5787253 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7860. Min Act: -0.1700
Data Index: 5787258 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 5618051 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 5618053 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 5908106 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7547. Min Act: -0.1700
Data Index: 2733996 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 2147349 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5787259 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 8460559 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5805660 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6922. Min Act: -0.1700
Data Index: 5787265 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6922. Min Act: -0.1700
Data Index: 631010 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6922. Min Act: -0.1700
Data Index: 5787256 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6610. Min Act: -0.1700
Data Index: 5618054 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6297. Min Act: -0.1700
Data Index: 5787249 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6610. Min Act: -0.1700
Data Index: 5618052 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9422. Min Range: -6.9422
Max Act: 6.6297. Min Act: -0.1700
Data Index: 3773922 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19