Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1216 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.6405. Min Act: -0.1700
Data Index: 7797498 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.5467. Min Act: -0.1700
Data Index: 4885297 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.5467. Min Act: -0.1700
Data Index: 6609534 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3905. Min Act: -0.1700
Data Index: 5551767 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3592. Min Act: -0.1700
Data Index: 5478256 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3280. Min Act: -0.1700
Data Index: 4220182 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2967. Min Act: -0.1700
Data Index: 3522357 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2342. Min Act: -0.1700
Data Index: 4220184 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2342. Min Act: -0.1700
Data Index: 4612484 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2030. Min Act: -0.1700
Data Index: 5478239 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2342. Min Act: -0.1700
Data Index: 3803 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1717. Min Act: -0.1700
Data Index: 1523493 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1717. Min Act: -0.1700
Data Index: 611974 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1717. Min Act: -0.1700
Data Index: 501384 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1717. Min Act: -0.1700
Data Index: 5960775 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1092. Min Act: -0.1700
Data Index: 7486473 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1092. Min Act: -0.1700
Data Index: 5669922 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1092. Min Act: -0.1700
Data Index: 8147323 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1092. Min Act: -0.1700
Data Index: 1990954 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.0780. Min Act: -0.1700
Data Index: 6444092 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19