Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.7114. Min Act: -0.1700
Data Index: 1298847 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.7114. Min Act: -0.1700
Data Index: 3181004 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.3989. Min Act: -0.1700
Data Index: 3050052 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.3364. Min Act: -0.1700
Data Index: 6160175 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.3364. Min Act: -0.1700
Data Index: 194695 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.2739. Min Act: -0.1700
Data Index: 1446418 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.2739. Min Act: -0.1695
Data Index: 8723119 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.1489. Min Act: -0.1700
Data Index: 5616125 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.0864. Min Act: -0.1700
Data Index: 3491850 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.0239. Min Act: -0.1700
Data Index: 8575951 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.0239. Min Act: -0.1700
Data Index: 7254716 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.0239. Min Act: -0.1700
Data Index: 631438 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7114. Min Range: -9.7114
Max Act: 9.0239. Min Act: -0.1700
Data Index: 833425 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.9614. Min Act: -0.1700
Data Index: 5976818 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.8364. Min Act: -0.1700
Data Index: 5164956 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.8989. Min Act: -0.1700
Data Index: 977681 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.8989. Min Act: -0.1700
Data Index: 978993 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.8364. Min Act: -0.1700
Data Index: 1247298 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.7739. Min Act: -0.1700
Data Index: 5584051 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7114. Min Range: -9.7114
Max Act: 8.8364. Min Act: -0.1700
Data Index: 6789460 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19