Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.9007. Min Act: -0.1700
Data Index: 636298 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.9163. Min Act: -0.1700
Data Index: 2900080 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7913. Min Act: -0.1700
Data Index: 7665687 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7756. Min Act: -0.1700
Data Index: 2929379 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.8225. Min Act: -0.1700
Data Index: 4626720 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7913. Min Act: -0.1700
Data Index: 6261176 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7600. Min Act: -0.1700
Data Index: 6875167 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7756. Min Act: -0.1700
Data Index: 3727280 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7600. Min Act: -0.1700
Data Index: 2100551 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7600. Min Act: -0.1700
Data Index: 1075889 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7443. Min Act: -0.1700
Data Index: 7000952 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7443. Min Act: -0.1700
Data Index: 737486 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7287. Min Act: -0.1700
Data Index: 4579585 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7287. Min Act: -0.1700
Data Index: 7558836 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7443. Min Act: -0.1700
Data Index: 956045 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7131. Min Act: -0.1700
Data Index: 2139566 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7131. Min Act: -0.1700
Data Index: 3995261 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.7287. Min Act: -0.1700
Data Index: 3585176 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.6818. Min Act: -0.1700
Data Index: 6292855 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9163. Min Range: -3.9163
Max Act: 3.6661. Min Act: -0.1700
Data Index: 7301298 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19