Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.6296. Min Act: -0.1700
Data Index: 2109638 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5983. Min Act: -0.1700
Data Index: 148173 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 277313 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 5913097 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5358. Min Act: -0.1700
Data Index: 2777926 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5358. Min Act: -0.1700
Data Index: 4053219 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 2858484 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 2183521 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4733. Min Act: -0.1700
Data Index: 5723578 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4421. Min Act: -0.1700
Data Index: 2810904 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4421. Min Act: -0.1700
Data Index: 1495525 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4421. Min Act: -0.1700
Data Index: 4053212 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4108. Min Act: -0.1700
Data Index: 5870768 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4108. Min Act: -0.1700
Data Index: 3209424 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4108. Min Act: -0.1700
Data Index: 7236404 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.3796. Min Act: -0.1700
Data Index: 1692082 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4108. Min Act: -0.1700
Data Index: 3267838 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.3796. Min Act: -0.1700
Data Index: 5437339 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.3796. Min Act: -0.1700
Data Index: 3554356 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.3796. Min Act: -0.1700
Data Index: 2973210 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19