Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.4809. Min Act: -0.1700
Data Index: 5469805 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.4184. Min Act: -0.1700
Data Index: 3829733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3872. Min Act: -0.1700
Data Index: 6516305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3872. Min Act: -0.1699
Data Index: 6684822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3872. Min Act: -0.1700
Data Index: 8336884 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 5279633 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 185050 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1161490 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 8678756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 8666108 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 7524226 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6952160 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6786493 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1910561 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6521890 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 6364981 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3559. Min Act: -0.1700
Data Index: 4113486 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.2934. Min Act: -0.1700
Data Index: 1108266 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3247. Min Act: -0.1700
Data Index: 3341467 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4809. Min Range: -4.4809
Max Act: 4.3247. Min Act: -0.1700
Data Index: 3501583 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19