Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.5796. Min Act: -0.1700
Data Index: 2487156 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.4858. Min Act: -0.1700
Data Index: 747102 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.3296. Min Act: -0.1700
Data Index: 404098 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.3608. Min Act: -0.1700
Data Index: 4752320 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2983. Min Act: -0.1700
Data Index: 6249301 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1149115 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2082798 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8424650 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2358. Min Act: -0.1700
Data Index: 8600346 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1733. Min Act: -0.1700
Data Index: 6967515 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.2046. Min Act: -0.1700
Data Index: 4376425 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1421. Min Act: -0.1700
Data Index: 7140169 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1421. Min Act: -0.1700
Data Index: 5932061 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1421. Min Act: -0.1700
Data Index: 4400974 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1421. Min Act: -0.1700
Data Index: 1903555 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.1108. Min Act: -0.1700
Data Index: 3557798 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.0796. Min Act: -0.1700
Data Index: 5437115 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.0796. Min Act: -0.1700
Data Index: 4555713 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.0483. Min Act: -0.1700
Data Index: 373694 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5796. Min Range: -6.5796
Max Act: 6.0483. Min Act: -0.1700
Data Index: 391274 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19