Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.7570. Min Act: -0.1700
Data Index: 2465965 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4133. Min Act: -0.1700
Data Index: 4148400 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2570. Min Act: -0.1700
Data Index: 1774021 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2570. Min Act: -0.1700
Data Index: 1568189 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2570. Min Act: -0.1700
Data Index: 8783501 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2882. Min Act: -0.1700
Data Index: 575638 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2570. Min Act: -0.1700
Data Index: 1390603 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.2257. Min Act: -0.1700
Data Index: 4525270 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1945. Min Act: -0.1700
Data Index: 7389013 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 1946681 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1945. Min Act: -0.1700
Data Index: 4371992 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 2683021 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 52275 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 3367653 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 4740087 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1632. Min Act: -0.1700
Data Index: 2087173 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1320. Min Act: -0.1700
Data Index: 6606767 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1320. Min Act: -0.1700
Data Index: 2492380 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.1320. Min Act: -0.1700
Data Index: 3602221 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.0695. Min Act: -0.1700
Data Index: 7389015 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19