Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.3261. Min Act: -0.1700
Data Index: 3051622 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2011. Min Act: -0.1700
Data Index: 5916019 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2324. Min Act: -0.1700
Data Index: 8357345 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2011. Min Act: -0.1700
Data Index: 4167529 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2011. Min Act: -0.1700
Data Index: 2988480 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2324. Min Act: -0.1700
Data Index: 6116288 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1699. Min Act: -0.1700
Data Index: 1609540 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 3499281 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1699. Min Act: -0.1700
Data Index: 4168680 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 130936 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 2087784 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 1547118 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1386. Min Act: -0.1700
Data Index: 6597016 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 4569430 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0761. Min Act: -0.1700
Data Index: 1748576 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0449. Min Act: -0.1700
Data Index: 270904 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0761. Min Act: -0.1700
Data Index: 2164742 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0761. Min Act: -0.1700
Data Index: 6105232 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0136. Min Act: -0.1700
Data Index: 2180384 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0449. Min Act: -0.1700
Data Index: 1088054 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19