Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.3180. Min Act: -0.1700
Data Index: 8832846 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.2867. Min Act: -0.1700
Data Index: 4209774 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.2242. Min Act: -0.1700
Data Index: 7530773 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.1617. Min Act: -0.1700
Data Index: 5346337 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.1617. Min Act: -0.1700
Data Index: 6983739 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.1617. Min Act: -0.1700
Data Index: 8727311 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.1305. Min Act: -0.1700
Data Index: 6902346 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.1305. Min Act: -0.1700
Data Index: 332201 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 63851 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3327144 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0992. Min Act: -0.1700
Data Index: 2413089 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 4169303 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 6772329 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 6448245 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 8021377 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0367. Min Act: -0.1700
Data Index: 4963411 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0367. Min Act: -0.1700
Data Index: 1594023 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0680. Min Act: -0.1700
Data Index: 1352526 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3180. Min Range: -6.3180
Max Act: 6.0367. Min Act: -0.1700
Data Index: 4114393 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3180. Min Range: -6.3180
Max Act: 5.9742. Min Act: -0.1700
Data Index: 7799506 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19