Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.9958. Min Act: -0.1700
Data Index: 5044408 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2897752 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.7458. Min Act: -0.1700
Data Index: 7492227 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.7458. Min Act: -0.1700
Data Index: 7381045 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.7458. Min Act: -0.1700
Data Index: 8388482 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.7458. Min Act: -0.1700
Data Index: 1945440 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6833. Min Act: -0.1700
Data Index: 7447263 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.7146. Min Act: -0.1700
Data Index: 6837827 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6833. Min Act: -0.1700
Data Index: 3355728 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6833. Min Act: -0.1700
Data Index: 1274537 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6521. Min Act: -0.1700
Data Index: 7649910 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6521. Min Act: -0.1700
Data Index: 5133618 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6521. Min Act: -0.1700
Data Index: 270079 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5350916 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6521. Min Act: -0.1700
Data Index: 5423524 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5613687 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6208. Min Act: -0.1700
Data Index: 8155944 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6521. Min Act: -0.1700
Data Index: 6896987 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6208. Min Act: -0.1700
Data Index: 2629633 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9958. Min Range: -4.9958
Max Act: 4.6208. Min Act: -0.1700
Data Index: 8060333 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19