Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0736. Min Act: -0.1700
Data Index: 6761543 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0424. Min Act: -0.1700
Data Index: 3351140 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0424. Min Act: -0.1700
Data Index: 5759982 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0424. Min Act: -0.1700
Data Index: 979688 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0111. Min Act: -0.1700
Data Index: 4339610 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0736. Min Range: -5.0736
Max Act: 5.0111. Min Act: -0.1700
Data Index: 4755864 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9486. Min Act: -0.1700
Data Index: 207349 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9799. Min Act: -0.1700
Data Index: 3864805 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9799. Min Act: -0.1700
Data Index: 3138183 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9799. Min Act: -0.1700
Data Index: 3090317 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9486. Min Act: -0.1700
Data Index: 1010389 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 6353820 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9486. Min Act: -0.1700
Data Index: 5098 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9486. Min Act: -0.1700
Data Index: 3593689 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 4078323 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9799. Min Act: -0.1700
Data Index: 511674 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 5299336 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3134858 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 5253530 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0736. Min Range: -5.0736
Max Act: 4.9174. Min Act: -0.1700
Data Index: 1801951 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19