Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2833. Min Range: -6.2833
Max Act: 6.2833. Min Act: -0.1700
Data Index: 6947909 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.8458. Min Act: -0.1700
Data Index: 6947908 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2334382 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.7208. Min Act: -0.1700
Data Index: 5675818 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.6895. Min Act: -0.1700
Data Index: 44029 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.6583. Min Act: -0.1700
Data Index: 6789264 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.6270. Min Act: -0.1700
Data Index: 5881225 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5958. Min Act: -0.1700
Data Index: 1925248 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.6270. Min Act: -0.1700
Data Index: 3391663 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5645. Min Act: -0.1700
Data Index: 7235127 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5645. Min Act: -0.1700
Data Index: 4158814 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5645. Min Act: -0.1700
Data Index: 8258179 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5333. Min Act: -0.1700
Data Index: 1090777 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5645. Min Act: -0.1700
Data Index: 5758213 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5645. Min Act: -0.1700
Data Index: 4697541 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5020. Min Act: -0.1700
Data Index: 6958948 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5333. Min Act: -0.1700
Data Index: 1601346 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.4708. Min Act: -0.1700
Data Index: 5880552 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5333. Min Act: -0.1700
Data Index: 6237623 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2833. Min Range: -6.2833
Max Act: 5.5020. Min Act: -0.1700
Data Index: 3881244 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19