Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.6456. Min Act: -0.1700
Data Index: 3523842 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.6456. Min Act: -0.1700
Data Index: 2708665 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.5831. Min Act: -0.1700
Data Index: 7254741 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.5831. Min Act: -0.1700
Data Index: 6657688 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.5206. Min Act: -0.1700
Data Index: 1269567 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.4893. Min Act: -0.1700
Data Index: 1477841 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.4581. Min Act: -0.1700
Data Index: 4905194 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3956. Min Act: -0.1700
Data Index: 3409614 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 4376335 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6222449 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3980531 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 7094399 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 4672365 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3643. Min Act: -0.1700
Data Index: 189916 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 2019417 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 5083531 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 3651467 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 3911436 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 6041191 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6456. Min Range: -5.6456
Max Act: 5.3331. Min Act: -0.1700
Data Index: 2964236 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19