Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.7730. Min Range: -16.7730
Max Act: 16.7730. Min Act: -0.1700
Data Index: 11634 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.7730. Min Range: -16.7730
Max Act: 15.0855. Min Act: -0.1700
Data Index: 6537220 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.9605. Min Act: -0.1700
Data Index: 743952 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.8355. Min Act: -0.1700
Data Index: 2454231 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.7730. Min Act: -0.1700
Data Index: 6407819 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.7730. Min Act: -0.1700
Data Index: 3331101 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.8355. Min Act: -0.1700
Data Index: 4352644 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.6480. Min Act: -0.1700
Data Index: 2502771 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.7105. Min Act: -0.1700
Data Index: 5928599 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.7730. Min Act: -0.1700
Data Index: 7876840 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5855. Min Act: -0.1700
Data Index: 270627 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5855. Min Act: -0.1700
Data Index: 6532949 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.4605. Min Act: -0.1700
Data Index: 8179314 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 4224263 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 272691 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 5655609 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 7065412 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 5629494 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.5230. Min Act: -0.1700
Data Index: 2832725 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.7730. Min Range: -16.7730
Max Act: 14.4605. Min Act: -0.1700
Data Index: 713203 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19