Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6352 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.7013. Min Act: -0.1700
Data Index: 8134503 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.6076. Min Act: -0.1700
Data Index: 972616 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.6388. Min Act: -0.1700
Data Index: 4821390 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.5763. Min Act: -0.1700
Data Index: 2494706 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.5451. Min Act: -0.1700
Data Index: 474635 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.5451. Min Act: -0.1700
Data Index: 7940564 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.5451. Min Act: -0.1700
Data Index: 3839615 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.4513. Min Act: -0.1700
Data Index: 6157085 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.3888. Min Act: -0.1700
Data Index: 3729552 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.3263. Min Act: -0.1700
Data Index: 1707521 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.3263. Min Act: -0.1700
Data Index: 6279615 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2951. Min Act: -0.1700
Data Index: 398408 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2638. Min Act: -0.1700
Data Index: 5554279 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2638. Min Act: -0.1700
Data Index: 5508839 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5324500 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2638. Min Act: -0.1700
Data Index: 4709183 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2326. Min Act: -0.1700
Data Index: 390515 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5174260 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2013. Min Act: -0.1700
Data Index: 5171357 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7013. Min Range: -6.7013
Max Act: 6.2013. Min Act: -0.1700
Data Index: 3871090 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19