Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3331. Min Range: -7.3331
Max Act: 7.3331. Min Act: -0.1700
Data Index: 8291938 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3331. Min Range: -7.3331
Max Act: 7.3018. Min Act: -0.1700
Data Index: 3585491 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3331. Min Range: -7.3331
Max Act: 7.1143. Min Act: -0.1700
Data Index: 203077 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3331. Min Range: -7.3331
Max Act: 7.0518. Min Act: -0.1700
Data Index: 7586469 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3331. Min Range: -7.3331
Max Act: 7.0206. Min Act: -0.1700
Data Index: 8291935 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.9893. Min Act: -0.1700
Data Index: 2530898 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.8956. Min Act: -0.1700
Data Index: 8348989 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.8956. Min Act: -0.1700
Data Index: 4006014 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.8643. Min Act: -0.1700
Data Index: 4442145 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.8643. Min Act: -0.1700
Data Index: 1367745 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.8018. Min Act: -0.1700
Data Index: 8291937 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.7081. Min Act: -0.1700
Data Index: 5676641 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.7081. Min Act: -0.1700
Data Index: 2361786 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.6768. Min Act: -0.1700
Data Index: 203075 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.6768. Min Act: -0.1700
Data Index: 8111778 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.6456. Min Act: -0.1700
Data Index: 8237470 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.6143. Min Act: -0.1700
Data Index: 8291934 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.6456. Min Act: -0.1700
Data Index: 7275151 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.5518. Min Act: -0.1700
Data Index: 7586467 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3331. Min Range: -7.3331
Max Act: 6.5831. Min Act: -0.1700
Data Index: 1123911 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19