Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.4108. Min Act: -0.1700
Data Index: 8198752 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.3483. Min Act: -0.1700
Data Index: 2678365 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.3483. Min Act: -0.1700
Data Index: 2699969 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.2546. Min Act: -0.1700
Data Index: 6982142 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.2546. Min Act: -0.1700
Data Index: 6080519 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.2858. Min Act: -0.1700
Data Index: 2798155 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.2233. Min Act: -0.1700
Data Index: 4807689 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.1296. Min Act: -0.1700
Data Index: 4605600 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.1296. Min Act: -0.1700
Data Index: 4773741 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.0983. Min Act: -0.1700
Data Index: 6538682 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.0983. Min Act: -0.1700
Data Index: 209472 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.0358. Min Act: -0.1700
Data Index: 8314762 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.0046. Min Act: -0.1700
Data Index: 1555635 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4108. Min Range: -5.4108
Max Act: 5.0046. Min Act: -0.1700
Data Index: 4860125 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.9733. Min Act: -0.1700
Data Index: 4254378 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.9733. Min Act: -0.1700
Data Index: 6650354 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.8796. Min Act: -0.1700
Data Index: 8220411 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1672467 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1445551 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4108. Min Range: -5.4108
Max Act: 4.9108. Min Act: -0.1700
Data Index: 6400805 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19