Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.9670. Min Act: -0.1700
Data Index: 1227609 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.9357. Min Act: -0.1700
Data Index: 4261818 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.9044. Min Act: -0.1700
Data Index: 7540944 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.9044. Min Act: -0.1700
Data Index: 6638221 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.8732. Min Act: -0.1700
Data Index: 4870767 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.8419. Min Act: -0.1700
Data Index: 3721492 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.8419. Min Act: -0.1700
Data Index: 2543824 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.8106. Min Act: -0.1700
Data Index: 1754982 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.8106. Min Act: -0.1700
Data Index: 3605715 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7481. Min Act: -0.1700
Data Index: 267802 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7481. Min Act: -0.1700
Data Index: 6638222 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7168. Min Act: -0.1700
Data Index: 2057955 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7794. Min Act: -0.1700
Data Index: 4398953 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7481. Min Act: -0.1700
Data Index: 758132 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7168. Min Act: -0.1700
Data Index: 4834011 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7168. Min Act: -0.1700
Data Index: 6298303 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7168. Min Act: -0.1700
Data Index: 2187157 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.6855. Min Act: -0.1700
Data Index: 6705563 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.6542. Min Act: -0.1700
Data Index: 2707158 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9670. Min Range: -3.9670
Max Act: 3.7168. Min Act: -0.1700
Data Index: 3451947 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19