Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.9924. Min Act: -0.1700
Data Index: 3779836 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4372121 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.7737. Min Act: -0.1700
Data Index: 6858234 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6799. Min Act: -0.1700
Data Index: 6604374 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.7112. Min Act: -0.1700
Data Index: 3092967 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.7112. Min Act: -0.1700
Data Index: 572093 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 3296182 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 1290127 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 2242237 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 7506549 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 7061353 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6487. Min Act: -0.1700
Data Index: 486247 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6174. Min Act: -0.1700
Data Index: 2347570 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6799. Min Act: -0.1700
Data Index: 5191075 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6174. Min Act: -0.1700
Data Index: 2994718 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.6174. Min Act: -0.1700
Data Index: 4532843 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.5862. Min Act: -0.1700
Data Index: 1651702 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.5862. Min Act: -0.1700
Data Index: 43111 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.5862. Min Act: -0.1700
Data Index: 6762131 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9924. Min Range: -6.9924
Max Act: 6.5862. Min Act: -0.1700
Data Index: 5978165 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19