Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.6685. Min Act: -0.1700
Data Index: 3356910 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.6372. Min Act: -0.1700
Data Index: 5478621 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.6216. Min Act: -0.1700
Data Index: 3368289 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.6216. Min Act: -0.1700
Data Index: 4730856 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.6059. Min Act: -0.1700
Data Index: 5681810 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5903. Min Act: -0.1700
Data Index: 6224340 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5903. Min Act: -0.1700
Data Index: 6666086 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5590. Min Act: -0.1700
Data Index: 6067801 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5590. Min Act: -0.1700
Data Index: 555085 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5746. Min Act: -0.1700
Data Index: 2401016 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5433. Min Act: -0.1700
Data Index: 1363998 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5277. Min Act: -0.1700
Data Index: 8778246 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5433. Min Act: -0.1700
Data Index: 556697 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.5277. Min Act: -0.1700
Data Index: 453090 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4807. Min Act: -0.1700
Data Index: 1997802 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4650. Min Act: -0.1700
Data Index: 7700109 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4807. Min Act: -0.1700
Data Index: 3641336 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4964. Min Act: -0.1700
Data Index: 3617964 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4650. Min Act: -0.1700
Data Index: 3832064 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6685. Min Range: -3.6685
Max Act: 3.4494. Min Act: -0.1700
Data Index: 1955474 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19