Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.2048. Min Act: -0.1700
Data Index: 1866614 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.1423. Min Act: -0.1700
Data Index: 3109473 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.1111. Min Act: -0.1700
Data Index: 5175186 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.1111. Min Act: -0.1700
Data Index: 410245 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0486. Min Act: -0.1700
Data Index: 7586434 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0798. Min Act: -0.1700
Data Index: 8316529 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0798. Min Act: -0.1700
Data Index: 2018381 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0798. Min Act: -0.1700
Data Index: 5376846 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0486. Min Act: -0.1700
Data Index: 5949800 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0486. Min Act: -0.1700
Data Index: 8359046 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0486. Min Act: -0.1700
Data Index: 824694 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0173. Min Act: -0.1700
Data Index: 6147715 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9861. Min Act: -0.1700
Data Index: 1993428 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9861. Min Act: -0.1700
Data Index: 6107130 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2048. Min Range: -7.2048
Max Act: 7.0173. Min Act: -0.1700
Data Index: 2066550 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9548. Min Act: -0.1700
Data Index: 3398666 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9548. Min Act: -0.1700
Data Index: 6745537 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9236. Min Act: -0.1700
Data Index: 3006367 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9236. Min Act: -0.1700
Data Index: 889066 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2048. Min Range: -7.2048
Max Act: 6.9236. Min Act: -0.1700
Data Index: 7115864 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19