Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.3276. Min Act: -0.1700
Data Index: 3448277 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.3276. Min Act: -0.1700
Data Index: 3017918 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.2963. Min Act: -0.1700
Data Index: 1272407 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3361656 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.2651. Min Act: -0.1700
Data Index: 6549158 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1713. Min Act: -0.1700
Data Index: 2361385 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1713. Min Act: -0.1700
Data Index: 2365364 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1401. Min Act: -0.1700
Data Index: 593300 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1401. Min Act: -0.1700
Data Index: 3362708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1401. Min Act: -0.1700
Data Index: 500810 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1401. Min Act: -0.1700
Data Index: 291731 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1401. Min Act: -0.1700
Data Index: 3129203 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.0776. Min Act: -0.1700
Data Index: 2334388 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1088. Min Act: -0.1700
Data Index: 8708934 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1088. Min Act: -0.1700
Data Index: 1389226 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.1088. Min Act: -0.1700
Data Index: 3099848 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.0776. Min Act: -0.1700
Data Index: 4935326 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.0463. Min Act: -0.1700
Data Index: 4518678 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.0463. Min Act: -0.1700
Data Index: 8568457 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3276. Min Range: -5.3276
Max Act: 5.0463. Min Act: -0.1700
Data Index: 423336 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19