Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 977 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.2142. Min Act: -0.1700
Data Index: 5759176 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.1830. Min Act: -0.1700
Data Index: 2247354 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.1517. Min Act: -0.1700
Data Index: 7400310 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.1205. Min Act: -0.1700
Data Index: 7694532 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0892. Min Act: -0.1700
Data Index: 1921000 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0892. Min Act: -0.1700
Data Index: 7846167 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0267. Min Act: -0.1700
Data Index: 6102742 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0267. Min Act: -0.1700
Data Index: 4767082 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0580. Min Act: -0.1700
Data Index: 300187 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0267. Min Act: -0.1700
Data Index: 3587783 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0580. Min Act: -0.1700
Data Index: 7433192 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2142. Min Range: -4.2142
Max Act: 4.0267. Min Act: -0.1700
Data Index: 3988230 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9954. Min Act: -0.1700
Data Index: 607458 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9954. Min Act: -0.1700
Data Index: 486861 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9954. Min Act: -0.1700
Data Index: 3959589 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9954. Min Act: -0.1700
Data Index: 3869912 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9329. Min Act: -0.1700
Data Index: 5686582 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9642. Min Act: -0.1700
Data Index: 6309877 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9329. Min Act: -0.1700
Data Index: 2827147 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2142. Min Range: -4.2142
Max Act: 3.9642. Min Act: -0.1700
Data Index: 1471283 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19