Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5935 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.7626. Min Act: -0.1700
Data Index: 7268754 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.7001. Min Act: -0.1700
Data Index: 66729 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.5126. Min Act: -0.1700
Data Index: 3720395 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.4188. Min Act: -0.1700
Data Index: 7321842 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.3251. Min Act: -0.1700
Data Index: 3604343 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.1063. Min Act: -0.1700
Data Index: 3322078 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0751. Min Act: -0.1700
Data Index: 7553218 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0751. Min Act: -0.1700
Data Index: 7759152 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0751. Min Act: -0.1700
Data Index: 1422672 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0751. Min Act: -0.1700
Data Index: 2028369 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0438. Min Act: -0.1700
Data Index: 4457145 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0438. Min Act: -0.1700
Data Index: 5631568 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0126. Min Act: -0.1700
Data Index: 3829779 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0126. Min Act: -0.1700
Data Index: 8463033 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7626. Min Range: -5.7626
Max Act: 5.0126. Min Act: -0.1700
Data Index: 7065214 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7626. Min Range: -5.7626
Max Act: 4.9813. Min Act: -0.1700
Data Index: 4416413 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7626. Min Range: -5.7626
Max Act: 4.9813. Min Act: -0.1700
Data Index: 2182747 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7626. Min Range: -5.7626
Max Act: 4.9501. Min Act: -0.1700
Data Index: 673524 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7626. Min Range: -5.7626
Max Act: 4.9501. Min Act: -0.1700
Data Index: 501866 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7626. Min Range: -5.7626
Max Act: 4.9188. Min Act: -0.1700
Data Index: 3271843 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19