Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2695. Min Range: -7.2695
Max Act: 7.2695. Min Act: -0.1700
Data Index: 2871165 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2695. Min Range: -7.2695
Max Act: 7.2070. Min Act: -0.1700
Data Index: 4501064 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.8945. Min Act: -0.1700
Data Index: 2358652 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.8945. Min Act: -0.1700
Data Index: 5957317 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.8632. Min Act: -0.1700
Data Index: 6175075 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7695. Min Act: -0.1700
Data Index: 8053573 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7695. Min Act: -0.1700
Data Index: 8398488 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7695. Min Act: -0.1700
Data Index: 565835 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7382. Min Act: -0.1700
Data Index: 2706912 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 3365663 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 8468592 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 7734620 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.7070. Min Act: -0.1700
Data Index: 8231330 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.6757. Min Act: -0.1700
Data Index: 8108743 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.6757. Min Act: -0.1700
Data Index: 283042 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 4964437 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 7575230 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.6132. Min Act: -0.1700
Data Index: 3797668 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.5820. Min Act: -0.1700
Data Index: 1035130 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2695. Min Range: -7.2695
Max Act: 6.5507. Min Act: -0.1700
Data Index: 5750592 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19