Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6051 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.3456. Min Act: -0.1700
Data Index: 2848447 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.3456. Min Act: -0.1700
Data Index: 7161766 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.3144. Min Act: -0.1700
Data Index: 8367799 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.3144. Min Act: -0.1700
Data Index: 538872 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.3144. Min Act: -0.1700
Data Index: 5259043 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.2831. Min Act: -0.1700
Data Index: 7197301 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.2519. Min Act: -0.1700
Data Index: 6528716 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.2206. Min Act: -0.1700
Data Index: 5570047 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.2206. Min Act: -0.1700
Data Index: 8464001 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.2206. Min Act: -0.1700
Data Index: 8180018 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1894. Min Act: -0.1700
Data Index: 587020 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1894. Min Act: -0.1700
Data Index: 3294596 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1894. Min Act: -0.1700
Data Index: 4532759 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1269. Min Act: -0.1700
Data Index: 5811822 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1581. Min Act: -0.1700
Data Index: 128747 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1581. Min Act: -0.1700
Data Index: 8165328 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1269. Min Act: -0.1700
Data Index: 6574797 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1581. Min Act: -0.1700
Data Index: 558391 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1581. Min Act: -0.1700
Data Index: 6207274 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3456. Min Range: -5.3456
Max Act: 5.1581. Min Act: -0.1700
Data Index: 3190207 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19