Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.6146. Min Act: -0.1700
Data Index: 4011259 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.5208. Min Act: -0.1700
Data Index: 7556578 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4896. Min Act: -0.1700
Data Index: 3969012 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4896. Min Act: -0.1700
Data Index: 7545341 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4896. Min Act: -0.1700
Data Index: 393352 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4583. Min Act: -0.1700
Data Index: 4164204 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4583. Min Act: -0.1700
Data Index: 3392284 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4583. Min Act: -0.1700
Data Index: 1075610 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4583. Min Act: -0.1700
Data Index: 1688639 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4583. Min Act: -0.1700
Data Index: 5326881 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4271. Min Act: -0.1700
Data Index: 2753742 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3958. Min Act: -0.1700
Data Index: 2640826 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.4271. Min Act: -0.1700
Data Index: 5039969 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3646. Min Act: -0.1700
Data Index: 4164203 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3646. Min Act: -0.1700
Data Index: 3779481 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3333. Min Act: -0.1700
Data Index: 1371432 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3646. Min Act: -0.1700
Data Index: 6541509 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3333. Min Act: -0.1700
Data Index: 6010971 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3021. Min Act: -0.1700
Data Index: 166225 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6146. Min Range: -4.6146
Max Act: 4.3333. Min Act: -0.1700
Data Index: 2928155 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19