Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1663 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6492. Min Act: -0.1700
Data Index: 7281220 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.6180. Min Act: -0.1700
Data Index: 2626629 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.5867. Min Act: -0.1700
Data Index: 1982830 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.4305. Min Act: -0.1700
Data Index: 8474275 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3680. Min Act: -0.1700
Data Index: 2689718 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3680. Min Act: -0.1700
Data Index: 8675534 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3680. Min Act: -0.1700
Data Index: 4313255 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7815515 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3367. Min Act: -0.1700
Data Index: 7655340 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3055. Min Act: -0.1700
Data Index: 5886379 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3055. Min Act: -0.1700
Data Index: 437258 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 1573021 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3055. Min Act: -0.1700
Data Index: 3915380 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3055. Min Act: -0.1700
Data Index: 632406 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 7234134 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 4358997 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.3055. Min Act: -0.1700
Data Index: 1042927 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 2300893 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 416216 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6492. Min Range: -4.6492
Max Act: 4.2742. Min Act: -0.1700
Data Index: 280016 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19