Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.4577. Min Act: -0.1700
Data Index: 1020037 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.2702. Min Act: -0.1700
Data Index: 5094693 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.3327. Min Act: -0.1700
Data Index: 767261 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.2077. Min Act: -0.1700
Data Index: 477828 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.1452. Min Act: -0.1700
Data Index: 1739352 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.1452. Min Act: -0.1700
Data Index: 4829087 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.0827. Min Act: -0.1700
Data Index: 5126233 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.0827. Min Act: -0.1700
Data Index: 7276164 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.1452. Min Act: -0.1700
Data Index: 5453296 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.9577. Min Act: -0.1700
Data Index: 1221559 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4577. Min Range: -15.4577
Max Act: 15.0202. Min Act: -0.1700
Data Index: 5909280 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.8327. Min Act: -0.1700
Data Index: 411805 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.8327. Min Act: -0.1700
Data Index: 4551063 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.8327. Min Act: -0.1699
Data Index: 8778941 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7702. Min Act: -0.1700
Data Index: 4882647 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7702. Min Act: -0.1700
Data Index: 7657370 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7702. Min Act: -0.1700
Data Index: 2274477 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7702. Min Act: -0.1700
Data Index: 3834350 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7077. Min Act: -0.1700
Data Index: 5050116 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4577. Min Range: -15.4577
Max Act: 14.7077. Min Act: -0.1700
Data Index: 2271160 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19