Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.3904. Min Act: -0.1700
Data Index: 3707567 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.3747. Min Act: -0.1700
Data Index: 5498377 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2963. Min Act: -0.1700
Data Index: 6808073 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.3120. Min Act: -0.1700
Data Index: 628118 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2963. Min Act: -0.1700
Data Index: 2891407 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2649. Min Act: -0.1700
Data Index: 5532063 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2806. Min Act: -0.1700
Data Index: 583209 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2649. Min Act: -0.1700
Data Index: 4664334 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2334. Min Act: -0.1700
Data Index: 392979 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2492. Min Act: -0.1700
Data Index: 5740802 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2492. Min Act: -0.1700
Data Index: 6611615 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1326947 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1011370 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2177. Min Act: -0.1700
Data Index: 4917768 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2177. Min Act: -0.1700
Data Index: 795431 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2177. Min Act: -0.1700
Data Index: 5380427 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2177. Min Act: -0.1700
Data Index: 3328462 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.2020. Min Act: -0.1700
Data Index: 4562752 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.1863. Min Act: -0.1700
Data Index: 388024 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3904. Min Range: -3.3904
Max Act: 3.1863. Min Act: -0.1700
Data Index: 3640007 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19