Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.9008. Min Act: -0.1700
Data Index: 3329650 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.5883. Min Act: -0.1700
Data Index: 1715456 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.5258. Min Act: -0.1700
Data Index: 7553606 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.4320. Min Act: -0.1700
Data Index: 265325 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.4008. Min Act: -0.1700
Data Index: 3099940 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.3070. Min Act: -0.1700
Data Index: 4639431 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.3070. Min Act: -0.1700
Data Index: 7459958 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.2758. Min Act: -0.1700
Data Index: 37802 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1820. Min Act: -0.1700
Data Index: 238208 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1508. Min Act: -0.1700
Data Index: 8229631 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1508. Min Act: -0.1700
Data Index: 2540839 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1508. Min Act: -0.1700
Data Index: 4536684 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1508. Min Act: -0.1700
Data Index: 4900045 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1195. Min Act: -0.1700
Data Index: 8668845 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1195. Min Act: -0.1700
Data Index: 8667686 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1195. Min Act: -0.1700
Data Index: 7558908 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.1195. Min Act: -0.1700
Data Index: 3676349 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.0258. Min Act: -0.1700
Data Index: 6000911 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.0570. Min Act: -0.1700
Data Index: 362965 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9008. Min Range: -7.9008
Max Act: 7.0258. Min Act: -0.1700
Data Index: 7642000 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19