Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5796 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.3700. Min Act: -0.1700
Data Index: 5793602 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.3700. Min Act: -0.1700
Data Index: 4635106 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.2137. Min Act: -0.1700
Data Index: 345848 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1049398 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1863095 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3700. Min Range: -7.3700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1743078 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.9950. Min Act: -0.1700
Data Index: 8140781 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.8075. Min Act: -0.1700
Data Index: 8465201 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.8075. Min Act: -0.1700
Data Index: 3767457 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.8075. Min Act: -0.1700
Data Index: 1122823 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.8075. Min Act: -0.1700
Data Index: 5980118 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.8075. Min Act: -0.1700
Data Index: 1751883 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7762. Min Act: -0.1700
Data Index: 8659982 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7450. Min Act: -0.1700
Data Index: 7381880 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7450. Min Act: -0.1700
Data Index: 7750469 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7450. Min Act: -0.1700
Data Index: 4212411 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7137. Min Act: -0.1700
Data Index: 2873993 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.7137. Min Act: -0.1700
Data Index: 7910427 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.6512. Min Act: -0.1700
Data Index: 1213467 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3700. Min Range: -7.3700
Max Act: 6.6825. Min Act: -0.1700
Data Index: 6811884 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19