Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0333. Min Range: -6.0333
Max Act: 6.0333. Min Act: -0.1700
Data Index: 8807573 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0333. Min Range: -6.0333
Max Act: 6.0333. Min Act: -0.1700
Data Index: 6166216 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.9396. Min Act: -0.1700
Data Index: 6371361 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.9083. Min Act: -0.1700
Data Index: 3529798 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8458. Min Act: -0.1700
Data Index: 3190262 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8458. Min Act: -0.1700
Data Index: 3147212 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8146. Min Act: -0.1700
Data Index: 3843093 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8146. Min Act: -0.1700
Data Index: 593775 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8146. Min Act: -0.1700
Data Index: 5582101 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.8146. Min Act: -0.1700
Data Index: 5026346 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.7521. Min Act: -0.1700
Data Index: 2347880 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.7208. Min Act: -0.1700
Data Index: 5800398 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3492143 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.7208. Min Act: -0.1700
Data Index: 4892112 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.7208. Min Act: -0.1700
Data Index: 4264682 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.6896. Min Act: -0.1700
Data Index: 4824349 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.6896. Min Act: -0.1700
Data Index: 3758163 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.6896. Min Act: -0.1700
Data Index: 3743249 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.6583. Min Act: -0.1700
Data Index: 7925101 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0333. Min Range: -6.0333
Max Act: 5.6583. Min Act: -0.1700
Data Index: 1076047 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19