Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.4206. Min Act: -0.1700
Data Index: 6898400 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.1393. Min Act: -0.1700
Data Index: 4141324 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.1081. Min Act: -0.1700
Data Index: 7253343 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0768. Min Act: -0.1700
Data Index: 7092368 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0456. Min Act: -0.1700
Data Index: 6928854 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9831. Min Act: -0.1700
Data Index: 819281 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0143. Min Act: -0.1700
Data Index: 613286 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0143. Min Act: -0.1700
Data Index: 3593934 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0143. Min Act: -0.1700
Data Index: 6418146 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9831. Min Act: -0.1700
Data Index: 878595 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8051020 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5853128 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9518. Min Act: -0.1700
Data Index: 1345737 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1728777 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4206. Min Range: -6.4206
Max Act: 6.0143. Min Act: -0.1700
Data Index: 6374862 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9518. Min Act: -0.1700
Data Index: 6038266 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9518. Min Act: -0.1700
Data Index: 6262510 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.8893. Min Act: -0.1700
Data Index: 471838 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.8893. Min Act: -0.1700
Data Index: 2769727 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4206. Min Range: -6.4206
Max Act: 5.9206. Min Act: -0.1700
Data Index: 4494005 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19