Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2290. Min Range: -7.2290
Max Act: 7.2290. Min Act: -0.1700
Data Index: 1889275 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2290. Min Range: -7.2290
Max Act: 7.1665. Min Act: -0.1700
Data Index: 3391943 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.9790. Min Act: -0.1700
Data Index: 1819050 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.9165. Min Act: -0.1700
Data Index: 5213869 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.9165. Min Act: -0.1700
Data Index: 3460076 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.8540. Min Act: -0.1700
Data Index: 7007597 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.8540. Min Act: -0.1700
Data Index: 1195658 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.8228. Min Act: -0.1700
Data Index: 2581275 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 5066668 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7603. Min Act: -0.1700
Data Index: 7867462 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 8432172 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7603. Min Act: -0.1700
Data Index: 804226 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 6758309 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 6869331 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 5939109 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 7541797 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 580695 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 1383963 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 2317428 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2290. Min Range: -7.2290
Max Act: 6.6978. Min Act: -0.1700
Data Index: 2577111 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19