Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0723. Min Range: -2.0723
Max Act: 2.0723. Min Act: -0.1700
Data Index: 7503549 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9542. Min Act: -0.1700
Data Index: 8174675 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9372. Min Act: -0.1700
Data Index: 6706017 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9372. Min Act: -0.1700
Data Index: 7282324 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9372. Min Act: -0.1700
Data Index: 2969940 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9031. Min Act: -0.1700
Data Index: 6397774 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9031. Min Act: -0.1700
Data Index: 6566595 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.9031. Min Act: -0.1700
Data Index: 6861293 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8861. Min Act: -0.1700
Data Index: 1694101 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8861. Min Act: -0.1700
Data Index: 3280680 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8861. Min Act: -0.1700
Data Index: 7743990 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8690. Min Act: -0.1700
Data Index: 3320067 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8690. Min Act: -0.1700
Data Index: 2103433 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8519. Min Act: -0.1700
Data Index: 7181058 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8519. Min Act: -0.1700
Data Index: 6945598 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8519. Min Act: -0.1700
Data Index: 4064646 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8690. Min Act: -0.1700
Data Index: 2737069 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8347. Min Act: -0.1700
Data Index: 4562344 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8690. Min Act: -0.1700
Data Index: 3288289 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8519. Min Act: -0.1700
Data Index: 2320520 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19