Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.9126. Min Act: -0.1700
Data Index: 1509586 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.6938. Min Act: -0.1700
Data Index: 4330381 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.6626. Min Act: -0.1700
Data Index: 349275 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.6001. Min Act: -0.1700
Data Index: 7133724 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.5688. Min Act: -0.1700
Data Index: 2334328 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.5063. Min Act: -0.1700
Data Index: 2123213 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.4751. Min Act: -0.1700
Data Index: 6380638 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.4126. Min Act: -0.1700
Data Index: 5140052 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.4438. Min Act: -0.1700
Data Index: 2171230 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.3813. Min Act: -0.1700
Data Index: 2191040 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.3813. Min Act: -0.1700
Data Index: 3203010 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.3188. Min Act: -0.1700
Data Index: 762415 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.3188. Min Act: -0.1700
Data Index: 482911 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.3188. Min Act: -0.1700
Data Index: 5946409 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2563. Min Act: -0.1700
Data Index: 2734579 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2876. Min Act: -0.1700
Data Index: 2930755 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2563. Min Act: -0.1700
Data Index: 4330382 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2251. Min Act: -0.1700
Data Index: 3965489 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2251. Min Act: -0.1700
Data Index: 1071451 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9126. Min Range: -6.9126
Max Act: 6.2563. Min Act: -0.1700
Data Index: 358315 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19