Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.9593. Min Act: -0.1700
Data Index: 660228 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.9593. Min Act: -0.1700
Data Index: 5301282 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.7718. Min Act: -0.1700
Data Index: 4186509 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6155. Min Act: -0.1700
Data Index: 3568648 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5843. Min Act: -0.1700
Data Index: 1291406 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5218. Min Act: -0.1700
Data Index: 4990964 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5530. Min Act: -0.1700
Data Index: 8408168 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5218. Min Act: -0.1700
Data Index: 1610845 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5530. Min Act: -0.1700
Data Index: 7542969 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4905. Min Act: -0.1700
Data Index: 2086275 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5218. Min Act: -0.1700
Data Index: 2179940 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4280. Min Act: -0.1700
Data Index: 1198378 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 686405 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.3968. Min Act: -0.1700
Data Index: 3269387 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.3968. Min Act: -0.1700
Data Index: 5495468 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.3343. Min Act: -0.1700
Data Index: 1017849 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.2718. Min Act: -0.1700
Data Index: 3212337 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.2405. Min Act: -0.1700
Data Index: 2405964 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.2093. Min Act: -0.1700
Data Index: 7935689 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.2093. Min Act: -0.1700
Data Index: 5784126 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19