Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.4807. Min Act: -0.1700
Data Index: 8240830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.4182. Min Act: -0.1700
Data Index: 1575974 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.4182. Min Act: -0.1700
Data Index: 4025468 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3870. Min Act: -0.1700
Data Index: 5868345 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3557. Min Act: -0.1700
Data Index: 1642633 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3245. Min Act: -0.1700
Data Index: 6479490 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1699
Data Index: 1728459 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 2599772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 2473004 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 8476118 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 3764050 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 1943687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 247391 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 5255429 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2620. Min Act: -0.1700
Data Index: 5367753 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 2707503 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 5441196 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2620. Min Act: -0.1700
Data Index: 2840868 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2620. Min Act: -0.1700
Data Index: 43545 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2620. Min Act: -0.1700
Data Index: 6264577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19