Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4097 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3730. Min Range: -8.3730
Max Act: 8.3730. Min Act: -0.1700
Data Index: 8060579 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3730. Min Range: -8.3730
Max Act: 8.3105. Min Act: -0.1700
Data Index: 3243806 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3730. Min Range: -8.3730
Max Act: 8.1855. Min Act: -0.1700
Data Index: 1228478 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3730. Min Range: -8.3730
Max Act: 8.0605. Min Act: -0.1700
Data Index: 3225819 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3730. Min Range: -8.3730
Max Act: 8.0605. Min Act: -0.1700
Data Index: 2030494 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9980. Min Act: -0.1700
Data Index: 4308381 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9980. Min Act: -0.1700
Data Index: 8100368 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9980. Min Act: -0.1700
Data Index: 4158794 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 6426372 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 6539763 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 6578100 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 3352745 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 7211227 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 4017040 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.9355. Min Act: -0.1700
Data Index: 7103471 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.8730. Min Act: -0.1700
Data Index: 3911889 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.8105. Min Act: -0.1700
Data Index: 4390155 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.8730. Min Act: -0.1700
Data Index: 2107831 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.8730. Min Act: -0.1700
Data Index: 4098196 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3730. Min Range: -8.3730
Max Act: 7.8105. Min Act: -0.1700
Data Index: 2981407 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19