Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2558. Min Range: -5.2558
Max Act: 5.2558. Min Act: -0.1700
Data Index: 2180232 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2558. Min Range: -5.2558
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4256083 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2558. Min Range: -5.2558
Max Act: 5.0058. Min Act: -0.1700
Data Index: 959693 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6616751 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.9121. Min Act: -0.1700
Data Index: 7623941 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.8183. Min Act: -0.1700
Data Index: 154835 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7871. Min Act: -0.1700
Data Index: 8180727 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7871. Min Act: -0.1700
Data Index: 365051 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7871. Min Act: -0.1700
Data Index: 3544565 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.8183. Min Act: -0.1700
Data Index: 620036 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7558. Min Act: -0.1700
Data Index: 5641150 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7558. Min Act: -0.1700
Data Index: 1059231 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7558. Min Act: -0.1700
Data Index: 1122148 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7246. Min Act: -0.1700
Data Index: 8337186 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7246. Min Act: -0.1700
Data Index: 3788417 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.7246. Min Act: -0.1700
Data Index: 5273152 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 3712678 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 1104977 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 3566965 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2558. Min Range: -5.2558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 3984148 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19