Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.8084. Min Act: -0.1700
Data Index: 4543886 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.8084. Min Act: -0.1700
Data Index: 7729047 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 7487832 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7772. Min Act: -0.1700
Data Index: 5453379 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7772. Min Act: -0.1700
Data Index: 7215223 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 416838 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 7710075 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 2933905 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 7529643 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7147. Min Act: -0.1700
Data Index: 242223 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7147. Min Act: -0.1700
Data Index: 8483617 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7459. Min Act: -0.1700
Data Index: 2790840 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 2629664 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4135681 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 715024 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 1338277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 6145738 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 327828 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.7147. Min Act: -0.1700
Data Index: 6735834 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8084. Min Range: -4.8084
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4862010 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19