Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6329. Min Range: -7.6329
Max Act: 7.6329. Min Act: -0.1700
Data Index: 4116625 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6329. Min Range: -7.6329
Max Act: 7.3204. Min Act: -0.1700
Data Index: 6631949 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6329. Min Range: -7.6329
Max Act: 7.1954. Min Act: -0.1700
Data Index: 1507721 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6329. Min Range: -7.6329
Max Act: 7.0392. Min Act: -0.1700
Data Index: 7048718 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6329. Min Range: -7.6329
Max Act: 7.0392. Min Act: -0.1700
Data Index: 5369040 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.9142. Min Act: -0.1700
Data Index: 7599272 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.9454. Min Act: -0.1700
Data Index: 193216 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.8829. Min Act: -0.1700
Data Index: 1746046 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.8829. Min Act: -0.1700
Data Index: 1679467 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.8829. Min Act: -0.1700
Data Index: 274201 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.8517. Min Act: -0.1700
Data Index: 3355417 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.8204. Min Act: -0.1700
Data Index: 783483 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7892. Min Act: -0.1700
Data Index: 2454671 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7579. Min Act: -0.1700
Data Index: 5344873 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7892. Min Act: -0.1700
Data Index: 3291284 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7892. Min Act: -0.1700
Data Index: 4736043 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7046100 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.7579. Min Act: -0.1700
Data Index: 5921225 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.6954. Min Act: -0.1700
Data Index: 3498704 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6329. Min Range: -7.6329
Max Act: 6.6954. Min Act: -0.1700
Data Index: 2669698 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19