Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4311 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.6526. Min Act: -0.1700
Data Index: 3564867 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.5901. Min Act: -0.1700
Data Index: 5615954 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.3088. Min Act: -0.1700
Data Index: 3422948 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.2463. Min Act: -0.1700
Data Index: 553352 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.1213. Min Act: -0.1700
Data Index: 6842585 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.1213. Min Act: -0.1700
Data Index: 2084120 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6526. Min Range: -8.6526
Max Act: 8.0588. Min Act: -0.1700
Data Index: 5942256 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.9651. Min Act: -0.1700
Data Index: 1825275 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.9338. Min Act: -0.1700
Data Index: 5157400 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.9338. Min Act: -0.1700
Data Index: 3282436 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.9026. Min Act: -0.1700
Data Index: 2537707 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.8088. Min Act: -0.1700
Data Index: 5999307 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.8088. Min Act: -0.1700
Data Index: 5904716 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.8088. Min Act: -0.1700
Data Index: 295769 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.7776. Min Act: -0.1700
Data Index: 6597252 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.7151. Min Act: -0.1700
Data Index: 7323711 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.7463. Min Act: -0.1700
Data Index: 1049800 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.7151. Min Act: -0.1700
Data Index: 4371056 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.7151. Min Act: -0.1700
Data Index: 2473031 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6526. Min Range: -8.6526
Max Act: 7.6526. Min Act: -0.1700
Data Index: 4485486 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19