Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7876109 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4921. Min Act: -0.1700
Data Index: 2857080 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4609. Min Act: -0.1700
Data Index: 5288363 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4296. Min Act: -0.1700
Data Index: 2758715 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4296. Min Act: -0.1700
Data Index: 1600703 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4296. Min Act: -0.1700
Data Index: 4638480 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.4296. Min Act: -0.1700
Data Index: 8308701 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3671. Min Act: -0.1700
Data Index: 6634659 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3671. Min Act: -0.1700
Data Index: 8547796 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3671. Min Act: -0.1700
Data Index: 1569093 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 2657524 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 1751167 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 4700535 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 682929 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 6670225 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.2734. Min Act: -0.1700
Data Index: 2597575 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 5651952 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.3046. Min Act: -0.1700
Data Index: 5189993 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.2734. Min Act: -0.1700
Data Index: 4339920 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5234. Min Range: -5.5234
Max Act: 5.2421. Min Act: -0.1700
Data Index: 2064859 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19