Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.8119. Min Act: -0.1700
Data Index: 6684060 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.8119. Min Act: -0.1700
Data Index: 3578310 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.7494. Min Act: -0.1700
Data Index: 3528997 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.6869. Min Act: -0.1700
Data Index: 965044 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.6244. Min Act: -0.1700
Data Index: 4126001 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5932. Min Act: -0.1700
Data Index: 381199 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5932. Min Act: -0.1700
Data Index: 2040771 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5932. Min Act: -0.1700
Data Index: 7661849 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5619. Min Act: -0.1700
Data Index: 2697489 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5932. Min Act: -0.1700
Data Index: 6065893 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5619. Min Act: -0.1700
Data Index: 3379748 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.4994. Min Act: -0.1700
Data Index: 8157823 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5307. Min Act: -0.1700
Data Index: 541491 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5140683 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5307. Min Act: -0.1700
Data Index: 137319 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.4994. Min Act: -0.1700
Data Index: 6349675 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4948301 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.4994. Min Act: -0.1700
Data Index: 934691 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.4994. Min Act: -0.1700
Data Index: 3296700 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8119. Min Range: -4.8119
Max Act: 4.4682. Min Act: -0.1700
Data Index: 5091158 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19