Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1517 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1163. Min Range: -7.1163
Max Act: 7.1163. Min Act: -0.1700
Data Index: 4853924 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 1901883 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.4913. Min Act: -0.1700
Data Index: 2259905 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 3785666 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 435038 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.4288. Min Act: -0.1700
Data Index: 1378057 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.3663. Min Act: -0.1700
Data Index: 5391540 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.3976. Min Act: -0.1700
Data Index: 476958 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.3663. Min Act: -0.1700
Data Index: 5526072 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.3663. Min Act: -0.1700
Data Index: 936016 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.3351. Min Act: -0.1700
Data Index: 4549589 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.2413. Min Act: -0.1700
Data Index: 2447713 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.2726. Min Act: -0.1700
Data Index: 6529019 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.2101. Min Act: -0.1700
Data Index: 2659994 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.1788. Min Act: -0.1700
Data Index: 6242410 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 2902669 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 7330894 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 5979563 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1163. Min Range: -7.1163
Max Act: 6.0851. Min Act: -0.1700
Data Index: 3531504 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1163. Min Range: -7.1163
Max Act: 5.9913. Min Act: -0.1700
Data Index: 3666224 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19