Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.3782. Min Act: -0.1700
Data Index: 815969 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.3290. Min Act: -0.1700
Data Index: 3524979 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2961. Min Act: -0.1700
Data Index: 753345 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.3126. Min Act: -0.1700
Data Index: 8313323 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2797. Min Act: -0.1700
Data Index: 6088656 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2797. Min Act: -0.1699
Data Index: 8545229 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2632. Min Act: -0.1700
Data Index: 2127082 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2301. Min Act: -0.1700
Data Index: 3901830 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2301. Min Act: -0.1700
Data Index: 3809625 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2301. Min Act: -0.1700
Data Index: 3168905 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2136. Min Act: -0.1700
Data Index: 1908048 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2301. Min Act: -0.1700
Data Index: 4580583 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2136. Min Act: -0.1700
Data Index: 6117766 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2136. Min Act: -0.1700
Data Index: 5806595 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.2136. Min Act: -0.1700
Data Index: 6061011 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.1804. Min Act: -0.1699
Data Index: 3092773 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.1804. Min Act: -0.1700
Data Index: 5312827 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.1804. Min Act: -0.1700
Data Index: 220521 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.1970. Min Act: -0.1700
Data Index: 7734336 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3782. Min Range: -2.3782
Max Act: 2.1637. Min Act: -0.1700
Data Index: 2456469 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19