Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2273 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.2610. Min Act: -0.1700
Data Index: 7365124 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.2298. Min Act: -0.1700
Data Index: 7705270 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.2610. Min Act: -0.1700
Data Index: 617536 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.2298. Min Act: -0.1700
Data Index: 6713855 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.2298. Min Act: -0.1700
Data Index: 6147396 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1985. Min Act: -0.1700
Data Index: 7981723 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1985. Min Act: -0.1700
Data Index: 5004867 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1673. Min Act: -0.1700
Data Index: 7816401 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1673. Min Act: -0.1700
Data Index: 7143774 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1673. Min Act: -0.1700
Data Index: 7656915 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1673. Min Act: -0.1700
Data Index: 4766034 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1360. Min Act: -0.1700
Data Index: 6860145 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1360. Min Act: -0.1700
Data Index: 192880 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1048. Min Act: -0.1700
Data Index: 3368673 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1360. Min Act: -0.1700
Data Index: 2770121 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1048. Min Act: -0.1700
Data Index: 4616654 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1048. Min Act: -0.1700
Data Index: 5909178 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.0735. Min Act: -0.1700
Data Index: 3768441 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1360. Min Act: -0.1700
Data Index: 2988624 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2610. Min Range: -4.2610
Max Act: 4.1048. Min Act: -0.1700
Data Index: 6394367 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19