Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.9164. Min Act: -0.1700
Data Index: 8235549 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.6976. Min Act: -0.1700
Data Index: 4686021 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.5101. Min Act: -0.1700
Data Index: 6189242 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.5414. Min Act: -0.1700
Data Index: 4477694 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.4789. Min Act: -0.1700
Data Index: 2452205 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.4476. Min Act: -0.1700
Data Index: 3048388 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.4164. Min Act: -0.1700
Data Index: 8532478 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.3851. Min Act: -0.1700
Data Index: 4513682 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.3539. Min Act: -0.1700
Data Index: 4748289 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.3851. Min Act: -0.1700
Data Index: 3980190 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.3226. Min Act: -0.1700
Data Index: 4518296 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.2914. Min Act: -0.1700
Data Index: 4544847 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.2914. Min Act: -0.1700
Data Index: 4033462 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.2601. Min Act: -0.1700
Data Index: 7732781 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.2289. Min Act: -0.1700
Data Index: 7575638 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.2289. Min Act: -0.1700
Data Index: 3793069 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.1976. Min Act: -0.1700
Data Index: 4789172 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.1039. Min Act: -0.1700
Data Index: 2093320 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.1664. Min Act: -0.1700
Data Index: 819614 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9164. Min Range: -7.9164
Max Act: 7.1664. Min Act: -0.1700
Data Index: 5587150 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19