Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 239 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2825. Min Act: -0.1680
Data Index: 6063563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2649. Min Act: -0.1700
Data Index: 6057363 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2473. Min Act: -0.1700
Data Index: 4763289 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2296. Min Act: -0.1699
Data Index: 1240143 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2296. Min Act: -0.1700
Data Index: 6377588 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.2120. Min Act: -0.1700
Data Index: 5363813 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1944. Min Act: -0.1700
Data Index: 4697415 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1856. Min Act: -0.1700
Data Index: 5088450 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1856. Min Act: -0.1700
Data Index: 1131521 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1680. Min Act: -0.1696
Data Index: 4007811 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1680. Min Act: -0.1700
Data Index: 1889469 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1768. Min Act: -0.1700
Data Index: 3294521 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1680. Min Act: -0.1700
Data Index: 6160126 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1592. Min Act: -0.1699
Data Index: 1658609 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1680. Min Act: -0.1700
Data Index: 1215901 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1592. Min Act: -0.1699
Data Index: 3854243 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1592. Min Act: -0.1700
Data Index: 2812257 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1680. Min Act: -0.1698
Data Index: 1889465 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1592. Min Act: -0.1700
Data Index: 6532392 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2825. Min Range: -1.2825
Max Act: 1.1592. Min Act: -0.1700
Data Index: 1001966 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19