Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8747. Min Act: -0.1693
Data Index: 6301124 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8576. Min Act: -0.1700
Data Index: 7670016 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8576. Min Act: -0.1700
Data Index: 968373 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8576. Min Act: -0.1700
Data Index: 2654065 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8404. Min Act: -0.1700
Data Index: 4409615 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8404. Min Act: -0.1700
Data Index: 5909972 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8404. Min Act: -0.1688
Data Index: 3386510 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8404. Min Act: -0.1679
Data Index: 8566473 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8319. Min Act: -0.1699
Data Index: 5062430 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8233. Min Act: -0.1700
Data Index: 3049279 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8319. Min Act: -0.1693
Data Index: 4094496 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8147. Min Act: -0.1696
Data Index: 8593767 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8319. Min Act: -0.1700
Data Index: 6161366 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8233. Min Act: -0.1700
Data Index: 3910159 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8233. Min Act: -0.1700
Data Index: 2291271 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8061. Min Act: -0.1699
Data Index: 759330 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8233. Min Act: -0.1700
Data Index: 2423701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8147. Min Act: -0.1700
Data Index: 5300860 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8061. Min Act: -0.1700
Data Index: 1200928 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8061. Min Act: -0.1682
Data Index: 3885055 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19