Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.6967. Min Act: -0.1700
Data Index: 812573 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.6342. Min Act: -0.1700
Data Index: 5316712 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.5717. Min Act: -0.1700
Data Index: 4109494 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.5404. Min Act: -0.1700
Data Index: 3606652 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.5404. Min Act: -0.1700
Data Index: 6646447 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.5404. Min Act: -0.1700
Data Index: 3301066 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.5092. Min Act: -0.1700
Data Index: 6165832 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4779. Min Act: -0.1700
Data Index: 7544070 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4467. Min Act: -0.1700
Data Index: 3465106 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4779. Min Act: -0.1700
Data Index: 2908502 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4779. Min Act: -0.1700
Data Index: 3465098 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4779. Min Act: -0.1700
Data Index: 807623 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4467. Min Act: -0.1700
Data Index: 7978567 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4154. Min Act: -0.1700
Data Index: 1847126 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4154. Min Act: -0.1700
Data Index: 557806 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.4154. Min Act: -0.1700
Data Index: 1469780 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.3842. Min Act: -0.1700
Data Index: 529118 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.3842. Min Act: -0.1700
Data Index: 2702536 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.3842. Min Act: -0.1700
Data Index: 3482397 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6967. Min Range: -6.6967
Max Act: 6.3842. Min Act: -0.1700
Data Index: 2104796 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19