Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5300 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.3874. Min Act: -0.1700
Data Index: 2307228 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.3562. Min Act: -0.1700
Data Index: 8266058 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.2937. Min Act: -0.1700
Data Index: 6246854 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.2312. Min Act: -0.1700
Data Index: 3593198 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.1999. Min Act: -0.1700
Data Index: 671582 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.1687. Min Act: -0.1700
Data Index: 1022285 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.1374. Min Act: -0.1700
Data Index: 5254068 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0437. Min Act: -0.1700
Data Index: 5253904 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0749. Min Act: -0.1700
Data Index: 4929748 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0749. Min Act: -0.1700
Data Index: 4535008 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0124. Min Act: -0.1700
Data Index: 4253199 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0437. Min Act: -0.1700
Data Index: 6570604 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0124. Min Act: -0.1700
Data Index: 883304 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0437. Min Act: -0.1700
Data Index: 8266059 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0749. Min Act: -0.1700
Data Index: 622243 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3874. Min Range: -7.3874
Max Act: 6.9812. Min Act: -0.1700
Data Index: 4814476 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3874. Min Range: -7.3874
Max Act: 7.0124. Min Act: -0.1700
Data Index: 5063833 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3874. Min Range: -7.3874
Max Act: 6.9812. Min Act: -0.1700
Data Index: 70790 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3874. Min Range: -7.3874
Max Act: 6.9499. Min Act: -0.1700
Data Index: 3262115 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3874. Min Range: -7.3874
Max Act: 6.9499. Min Act: -0.1700
Data Index: 7891254 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19