Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4389 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.4277. Min Act: -0.1700
Data Index: 220868 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.3027. Min Act: -0.1700
Data Index: 1823182 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.3027. Min Act: -0.1700
Data Index: 8365003 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.2402. Min Act: -0.1700
Data Index: 4992877 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.3027. Min Act: -0.1700
Data Index: 5061937 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 6193476 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 1340801 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 8324663 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 7884270 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 5726674 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 7466968 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 7182712 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 6916325 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 5613595 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 2039986 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 353693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 3748617 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 6022166 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1777. Min Act: -0.1700
Data Index: 6014773 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4277. Min Range: -15.4277
Max Act: 15.1152. Min Act: -0.1700
Data Index: 3379291 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19