Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.6893. Min Act: -0.1700
Data Index: 240059 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.6268. Min Act: -0.1700
Data Index: 4117416 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.5643. Min Act: -0.1700
Data Index: 3789600 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.2831. Min Act: -0.1700
Data Index: 4516785 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.0331. Min Act: -0.1700
Data Index: 4215687 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.0643. Min Act: -0.1700
Data Index: 5857739 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.0331. Min Act: -0.1700
Data Index: 1979798 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6893. Min Range: -7.6893
Max Act: 7.0018. Min Act: -0.1700
Data Index: 8077043 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.8768. Min Act: -0.1700
Data Index: 2254606 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.8456. Min Act: -0.1700
Data Index: 8170294 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.8143. Min Act: -0.1700
Data Index: 2032425 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.6581. Min Act: -0.1700
Data Index: 7155013 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.6581. Min Act: -0.1700
Data Index: 6974135 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.6581. Min Act: -0.1700
Data Index: 3945228 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.6581. Min Act: -0.1700
Data Index: 8664160 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.5643. Min Act: -0.1700
Data Index: 475809 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.5956. Min Act: -0.1700
Data Index: 460918 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.6268. Min Act: -0.1700
Data Index: 591235 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.5643. Min Act: -0.1700
Data Index: 7394927 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6893. Min Range: -7.6893
Max Act: 6.5018. Min Act: -0.1700
Data Index: 7114216 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19