Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3183. Min Range: -4.3183
Max Act: 4.3183. Min Act: -0.1700
Data Index: 5608644 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3183. Min Range: -4.3183
Max Act: 4.0682. Min Act: -0.1700
Data Index: 1402004 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.9119. Min Act: -0.1700
Data Index: 2335283 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.9119. Min Act: -0.1700
Data Index: 473556 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.9119. Min Act: -0.1700
Data Index: 2840551 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.8807. Min Act: -0.1700
Data Index: 2886136 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.8181. Min Act: -0.1700
Data Index: 5183667 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.8181. Min Act: -0.1700
Data Index: 5294296 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7868. Min Act: -0.1700
Data Index: 2925655 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7556. Min Act: -0.1700
Data Index: 5536714 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7556. Min Act: -0.1700
Data Index: 2377175 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7556. Min Act: -0.1700
Data Index: 2266153 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7556. Min Act: -0.1700
Data Index: 596593 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7243. Min Act: -0.1700
Data Index: 4357216 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.6930. Min Act: -0.1700
Data Index: 5372043 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7243. Min Act: -0.1700
Data Index: 5970823 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7243. Min Act: -0.1700
Data Index: 1924488 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7243. Min Act: -0.1700
Data Index: 3843556 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.7243. Min Act: -0.1700
Data Index: 3334489 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3183. Min Range: -4.3183
Max Act: 3.6930. Min Act: -0.1700
Data Index: 2609288 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19