Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5747 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8897. Min Act: -0.1700
Data Index: 5988978 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8584. Min Act: -0.1700
Data Index: 4338088 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8584. Min Act: -0.1700
Data Index: 3071385 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8584. Min Act: -0.1700
Data Index: 7320696 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8584. Min Act: -0.1700
Data Index: 4416911 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 2671666 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 6546934 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 6519515 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 1606994 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 5780246 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 5683169 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 3250791 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 1992309 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.8271. Min Act: -0.1700
Data Index: 3175509 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 3435349 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 5815813 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 3445406 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 669212 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 5895831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8897. Min Range: -3.8897
Max Act: 3.7958. Min Act: -0.1700
Data Index: 1588535 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19