Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.6112. Min Act: -0.1700
Data Index: 6658529 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.5800. Min Act: -0.1700
Data Index: 7781699 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1959895 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.5175. Min Act: -0.1700
Data Index: 3249897 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.5487. Min Act: -0.1700
Data Index: 2832162 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.4550. Min Act: -0.1700
Data Index: 1392217 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.4237. Min Act: -0.1700
Data Index: 2591238 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.4237. Min Act: -0.1700
Data Index: 4170960 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.4237. Min Act: -0.1700
Data Index: 4398445 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 5127972 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 2986454 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 7001980 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 6450566 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 3399513 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3925. Min Act: -0.1700
Data Index: 5113511 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3612. Min Act: -0.1700
Data Index: 7314723 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3612. Min Act: -0.1700
Data Index: 4184131 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3612. Min Act: -0.1700
Data Index: 3661908 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3612. Min Act: -0.1700
Data Index: 2650615 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6112. Min Range: -5.6112
Max Act: 5.3612. Min Act: -0.1700
Data Index: 5782847 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19