Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.9482. Min Act: -0.1700
Data Index: 168346 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.5732. Min Act: -0.1700
Data Index: 1038582 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 3407777 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 3864207 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.3857. Min Act: -0.1700
Data Index: 4880551 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.4482. Min Act: -0.1700
Data Index: 3490060 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.3232. Min Act: -0.1700
Data Index: 5012197 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.3232. Min Act: -0.1700
Data Index: 1941143 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 6334620 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 7556810 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1982. Min Act: -0.1700
Data Index: 2946200 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 7759199 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 1517119 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 2567132 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 2444957 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1982. Min Act: -0.1700
Data Index: 7533929 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1982. Min Act: -0.1700
Data Index: 3301317 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1982. Min Act: -0.1700
Data Index: 1971484 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1982. Min Act: -0.1700
Data Index: 420381 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9482. Min Range: -9.9482
Max Act: 9.1357. Min Act: -0.1700
Data Index: 1810726 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19