Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1304. Min Range: -6.1304
Max Act: 6.1304. Min Act: -0.1700
Data Index: 4432963 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6800055 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.9429. Min Act: -0.1700
Data Index: 6863644 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.9116. Min Act: -0.1700
Data Index: 594778 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.9116. Min Act: -0.1700
Data Index: 1797771 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.8179. Min Act: -0.1700
Data Index: 7312145 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3892928 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7554. Min Act: -0.1700
Data Index: 1384435 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2661151 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7554. Min Act: -0.1700
Data Index: 2778108 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7241. Min Act: -0.1700
Data Index: 3092564 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7241. Min Act: -0.1700
Data Index: 6399059 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.7554. Min Act: -0.1700
Data Index: 8561805 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.6929. Min Act: -0.1700
Data Index: 8212238 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.6304. Min Act: -0.1700
Data Index: 6307039 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.6304. Min Act: -0.1700
Data Index: 6861720 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.5991. Min Act: -0.1700
Data Index: 3059873 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.5679. Min Act: -0.1700
Data Index: 3749312 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.5991. Min Act: -0.1700
Data Index: 555808 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1304. Min Range: -6.1304
Max Act: 5.5991. Min Act: -0.1700
Data Index: 4088624 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19