Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4908 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.6865. Min Act: -0.1700
Data Index: 1632816 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.4990. Min Act: -0.1700
Data Index: 4501335 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.4053. Min Act: -0.1700
Data Index: 5703273 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.4053. Min Act: -0.1700
Data Index: 24811 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.3740. Min Act: -0.1700
Data Index: 662386 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.3428. Min Act: -0.1700
Data Index: 6347992 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.3428. Min Act: -0.1700
Data Index: 2750208 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.2178. Min Act: -0.1700
Data Index: 3667781 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.2178. Min Act: -0.1700
Data Index: 7000163 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.1240. Min Act: -0.1700
Data Index: 37905 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0928. Min Act: -0.1700
Data Index: 4874689 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.1553. Min Act: -0.1700
Data Index: 8812259 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0928. Min Act: -0.1700
Data Index: 7148459 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0928. Min Act: -0.1700
Data Index: 5859831 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0615. Min Act: -0.1700
Data Index: 5949579 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0615. Min Act: -0.1700
Data Index: 7557130 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0615. Min Act: -0.1700
Data Index: 1067946 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0615. Min Act: -0.1700
Data Index: 2978019 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0615. Min Act: -0.1700
Data Index: 5538743 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6865. Min Range: -6.6865
Max Act: 6.0303. Min Act: -0.1700
Data Index: 2101350 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19