Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1791. Min Range: -7.1791
Max Act: 7.1791. Min Act: -0.1700
Data Index: 1246535 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1791. Min Range: -7.1791
Max Act: 7.1479. Min Act: -0.1700
Data Index: 4603947 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1791. Min Range: -7.1791
Max Act: 7.0229. Min Act: -0.1700
Data Index: 5512769 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.9916. Min Act: -0.1700
Data Index: 8115974 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.9291. Min Act: -0.1700
Data Index: 5736609 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.9604. Min Act: -0.1700
Data Index: 2436069 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.9291. Min Act: -0.1700
Data Index: 91095 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8979. Min Act: -0.1700
Data Index: 5194113 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8666. Min Act: -0.1700
Data Index: 5512768 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8354. Min Act: -0.1700
Data Index: 106806 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8354. Min Act: -0.1700
Data Index: 763946 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 623321 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 3549818 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 6140089 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 7145615 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 7726638 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 1780782 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.8041. Min Act: -0.1700
Data Index: 2779025 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.7729. Min Act: -0.1700
Data Index: 5777175 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1791. Min Range: -7.1791
Max Act: 6.7729. Min Act: -0.1700
Data Index: 4163348 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19