Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.4699. Min Act: -0.1700
Data Index: 6043527 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.4074. Min Act: -0.1700
Data Index: 4715736 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.3761. Min Act: -0.1700
Data Index: 3451732 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.3449. Min Act: -0.1700
Data Index: 4716298 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.3136. Min Act: -0.1700
Data Index: 5899802 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2153955 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2824. Min Act: -0.1700
Data Index: 3429420 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2824. Min Act: -0.1700
Data Index: 596330 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2199. Min Act: -0.1700
Data Index: 8830336 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2225774 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.2199. Min Act: -0.1700
Data Index: 6077576 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1574. Min Act: -0.1700
Data Index: 4980036 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1886. Min Act: -0.1700
Data Index: 1335152 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1886. Min Act: -0.1700
Data Index: 3410943 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1886. Min Act: -0.1700
Data Index: 6750723 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1574. Min Act: -0.1700
Data Index: 3809218 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2874626 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.0949. Min Act: -0.1700
Data Index: 2607303 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2094508 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4699. Min Range: -5.4699
Max Act: 5.1261. Min Act: -0.1700
Data Index: 4025108 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19