Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1343. Min Range: -6.1343
Max Act: 6.1343. Min Act: -0.1700
Data Index: 5251036 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1343. Min Range: -6.1343
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4645072 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.8843. Min Act: -0.1700
Data Index: 2655292 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4885539 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.9156. Min Act: -0.1700
Data Index: 7858521 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.8843. Min Act: -0.1700
Data Index: 1371913 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.8531. Min Act: -0.1700
Data Index: 8047919 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7906. Min Act: -0.1700
Data Index: 1819154 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.8531. Min Act: -0.1700
Data Index: 7446579 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.8218. Min Act: -0.1700
Data Index: 3153658 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7906. Min Act: -0.1700
Data Index: 7281495 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7906. Min Act: -0.1700
Data Index: 1715644 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7906. Min Act: -0.1700
Data Index: 7271448 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7906. Min Act: -0.1700
Data Index: 663960 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5699257 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7281. Min Act: -0.1700
Data Index: 5790356 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.7281. Min Act: -0.1700
Data Index: 2454317 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.6968. Min Act: -0.1700
Data Index: 4922542 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.6968. Min Act: -0.1700
Data Index: 40154 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1343. Min Range: -6.1343
Max Act: 5.6968. Min Act: -0.1700
Data Index: 7709736 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19