Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.6780. Min Act: -0.1700
Data Index: 709679 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.5217. Min Act: -0.1700
Data Index: 7170475 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.4280. Min Act: -0.1700
Data Index: 1237540 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.3967. Min Act: -0.1700
Data Index: 8194223 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.3967. Min Act: -0.1700
Data Index: 1053211 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2717. Min Act: -0.1700
Data Index: 7542781 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.3030. Min Act: -0.1700
Data Index: 5484736 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2717. Min Act: -0.1700
Data Index: 706999 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.3030. Min Act: -0.1700
Data Index: 1836688 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2717. Min Act: -0.1700
Data Index: 6983644 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2717. Min Act: -0.1700
Data Index: 2444977 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2405. Min Act: -0.1700
Data Index: 8422507 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2405. Min Act: -0.1700
Data Index: 1667051 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2405. Min Act: -0.1700
Data Index: 1121142 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.2092. Min Act: -0.1700
Data Index: 2184133 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.1780. Min Act: -0.1700
Data Index: 4966502 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.1780. Min Act: -0.1700
Data Index: 2594251 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.1467. Min Act: -0.1700
Data Index: 5257029 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.1467. Min Act: -0.1700
Data Index: 934302 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6780. Min Range: -6.6780
Max Act: 6.1467. Min Act: -0.1700
Data Index: 594658 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19