Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.8476. Min Act: -0.1700
Data Index: 3304946 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7961. Min Act: -0.1700
Data Index: 8370140 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7616. Min Act: -0.1700
Data Index: 1475264 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7444. Min Act: -0.1700
Data Index: 4798696 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7616. Min Act: -0.1700
Data Index: 6992943 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7271. Min Act: -0.1700
Data Index: 5663188 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7097. Min Act: -0.1700
Data Index: 1398607 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7097. Min Act: -0.1700
Data Index: 3777420 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7097. Min Act: -0.1700
Data Index: 6968438 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7097. Min Act: -0.1700
Data Index: 5663190 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.7097. Min Act: -0.1700
Data Index: 8599500 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6924. Min Act: -0.1700
Data Index: 1292950 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6924. Min Act: -0.1700
Data Index: 3804908 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6750. Min Act: -0.1700
Data Index: 975817 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6750. Min Act: -0.1700
Data Index: 2114327 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6750. Min Act: -0.1700
Data Index: 8567545 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6750. Min Act: -0.1700
Data Index: 1186002 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6577. Min Act: -0.1700
Data Index: 5755156 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6577. Min Act: -0.1700
Data Index: 518431 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8476. Min Range: -1.8476
Max Act: 1.6577. Min Act: -0.1700
Data Index: 2323640 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19