Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2453. Min Range: -7.2453
Max Act: 7.2453. Min Act: -0.1700
Data Index: 93529 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.9641. Min Act: -0.1700
Data Index: 3036519 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.9641. Min Act: -0.1700
Data Index: 6838793 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.6828. Min Act: -0.1700
Data Index: 5920667 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.6516. Min Act: -0.1700
Data Index: 365595 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.6203. Min Act: -0.1700
Data Index: 4676591 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5891. Min Act: -0.1700
Data Index: 3156017 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5578. Min Act: -0.1700
Data Index: 8120408 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5578. Min Act: -0.1700
Data Index: 1913597 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5578. Min Act: -0.1700
Data Index: 2757013 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5266. Min Act: -0.1700
Data Index: 6331918 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5266. Min Act: -0.1700
Data Index: 3589610 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5266. Min Act: -0.1700
Data Index: 7772188 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.5266. Min Act: -0.1700
Data Index: 6851563 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4953. Min Act: -0.1700
Data Index: 2638474 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4953. Min Act: -0.1700
Data Index: 6626288 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4641. Min Act: -0.1700
Data Index: 4443145 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4641. Min Act: -0.1700
Data Index: 6955482 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4641. Min Act: -0.1700
Data Index: 3205818 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2453. Min Range: -7.2453
Max Act: 6.4641. Min Act: -0.1700
Data Index: 7048230 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19