Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5958 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3445. Min Range: -6.3445
Max Act: 6.3445. Min Act: -0.1700
Data Index: 7898435 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3445. Min Range: -6.3445
Max Act: 6.2508. Min Act: -0.1700
Data Index: 7464761 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3445. Min Range: -6.3445
Max Act: 6.0633. Min Act: -0.1700
Data Index: 3077806 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3445. Min Range: -6.3445
Max Act: 6.0008. Min Act: -0.1700
Data Index: 75413 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.9070. Min Act: -0.1700
Data Index: 5638885 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.8758. Min Act: -0.1700
Data Index: 2373132 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.8133. Min Act: -0.1700
Data Index: 8267198 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.8133. Min Act: -0.1700
Data Index: 8396873 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.8133. Min Act: -0.1700
Data Index: 3594635 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7820. Min Act: -0.1700
Data Index: 2126419 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7508. Min Act: -0.1700
Data Index: 1123646 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7508. Min Act: -0.1700
Data Index: 1746234 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7195. Min Act: -0.1700
Data Index: 187432 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7195. Min Act: -0.1700
Data Index: 7470432 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.7195. Min Act: -0.1700
Data Index: 6016236 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.6883. Min Act: -0.1700
Data Index: 4427611 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.6883. Min Act: -0.1700
Data Index: 7234933 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 6301490 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 6116214 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3445. Min Range: -6.3445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 7657965 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19