Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.5654. Min Act: -0.1700
Data Index: 8454708 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.5654. Min Act: -0.1700
Data Index: 593515 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3985. Min Act: -0.1700
Data Index: 2251255 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3985. Min Act: -0.1700
Data Index: 7636406 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3985. Min Act: -0.1700
Data Index: 5386218 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3985. Min Act: -0.1699
Data Index: 2118699 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3809. Min Act: -0.1700
Data Index: 4309067 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3897. Min Act: -0.1700
Data Index: 196855 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3720. Min Act: -0.1697
Data Index: 6780604 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3720. Min Act: -0.1700
Data Index: 5109083 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3632. Min Act: -0.1700
Data Index: 1809146 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3720. Min Act: -0.1700
Data Index: 3172112 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3720. Min Act: -0.1700
Data Index: 698928 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3544. Min Act: -0.1700
Data Index: 1119559 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3632. Min Act: -0.1700
Data Index: 5352552 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3544. Min Act: -0.1700
Data Index: 2575445 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3632. Min Act: -0.1700
Data Index: 4761534 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3544. Min Act: -0.1700
Data Index: 1099888 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3720. Min Act: -0.1699
Data Index: 762335 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5654. Min Range: -1.5654
Max Act: 1.3632. Min Act: -0.1700
Data Index: 1329437 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19