Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5473 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.5805. Min Act: -0.1700
Data Index: 2677657 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.4867. Min Act: -0.1700
Data Index: 134030 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.3617. Min Act: -0.1700
Data Index: 7224016 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.3305. Min Act: -0.1700
Data Index: 5813789 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.3305. Min Act: -0.1700
Data Index: 6619195 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.3617. Min Act: -0.1700
Data Index: 3532277 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2992. Min Act: -0.1700
Data Index: 4901279 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2992. Min Act: -0.1700
Data Index: 4271801 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2367. Min Act: -0.1700
Data Index: 7673141 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2680. Min Act: -0.1700
Data Index: 7938535 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2367. Min Act: -0.1700
Data Index: 1575452 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2367. Min Act: -0.1700
Data Index: 893374 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.2367. Min Act: -0.1700
Data Index: 6309289 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6392772 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1430. Min Act: -0.1700
Data Index: 8191778 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1742. Min Act: -0.1700
Data Index: 577762 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1742. Min Act: -0.1700
Data Index: 8191767 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1742. Min Act: -0.1700
Data Index: 2825480 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1742. Min Act: -0.1700
Data Index: 7339903 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5805. Min Range: -4.5805
Max Act: 4.1430. Min Act: -0.1700
Data Index: 649060 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19