Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.5051. Min Act: -0.1700
Data Index: 611961 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.3749. Min Act: -0.1700
Data Index: 2104999 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.3585. Min Act: -0.1700
Data Index: 5909144 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.3421. Min Act: -0.1700
Data Index: 2559014 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2929. Min Act: -0.1700
Data Index: 1113050 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2929. Min Act: -0.1700
Data Index: 2291803 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2929. Min Act: -0.1700
Data Index: 4184487 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2929. Min Act: -0.1700
Data Index: 6299959 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2929. Min Act: -0.1700
Data Index: 2559007 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 5370508 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 4825615 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 5567071 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2599. Min Act: -0.1700
Data Index: 2743866 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 6469553 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 1061065 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2764. Min Act: -0.1700
Data Index: 446370 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2599. Min Act: -0.1700
Data Index: 8666574 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2268. Min Act: -0.1700
Data Index: 2535179 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2599. Min Act: -0.1700
Data Index: 3459194 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5051. Min Range: -2.5051
Max Act: 2.2268. Min Act: -0.1700
Data Index: 877850 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19