Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1879 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.7730. Min Act: -0.1700
Data Index: 7687425 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.7105. Min Act: -0.1700
Data Index: 973318 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.5543. Min Act: -0.1700
Data Index: 5855047 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6810681 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.3668. Min Act: -0.1700
Data Index: 2100126 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.3355. Min Act: -0.1700
Data Index: 4965283 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.3355. Min Act: -0.1700
Data Index: 3394625 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.3355. Min Act: -0.1700
Data Index: 5560757 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.2730. Min Act: -0.1700
Data Index: 8816354 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.2418. Min Act: -0.1700
Data Index: 2687845 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.2418. Min Act: -0.1700
Data Index: 6489598 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.2418. Min Act: -0.1700
Data Index: 4707698 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.2105. Min Act: -0.1700
Data Index: 1290353 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1793. Min Act: -0.1700
Data Index: 1411108 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1480. Min Act: -0.1700
Data Index: 2448262 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1480. Min Act: -0.1700
Data Index: 3820056 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1480. Min Act: -0.1700
Data Index: 4554897 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1168. Min Act: -0.1700
Data Index: 1378029 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1168. Min Act: -0.1700
Data Index: 5959368 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7730. Min Range: -5.7730
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4833517 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19