Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5811. Min Act: -0.1700
Data Index: 8788201 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 8741457 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.4561. Min Act: -0.1700
Data Index: 208482 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.3936. Min Act: -0.1700
Data Index: 7142597 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.3936. Min Act: -0.1700
Data Index: 3602232 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.3311. Min Act: -0.1700
Data Index: 5151839 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2999. Min Act: -0.1700
Data Index: 7441534 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2999. Min Act: -0.1700
Data Index: 1931984 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2999. Min Act: -0.1700
Data Index: 6091190 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2999. Min Act: -0.1700
Data Index: 6444621 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2999. Min Act: -0.1700
Data Index: 7067114 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2686. Min Act: -0.1700
Data Index: 3364285 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2061. Min Act: -0.1700
Data Index: 2138499 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2061. Min Act: -0.1700
Data Index: 6595888 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2061. Min Act: -0.1700
Data Index: 6825540 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2374. Min Act: -0.1700
Data Index: 208481 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2374. Min Act: -0.1700
Data Index: 3524156 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2374. Min Act: -0.1700
Data Index: 1128128 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2374. Min Act: -0.1700
Data Index: 4303910 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.2061. Min Act: -0.1700
Data Index: 4719974 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19