Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1587. Min Range: -4.1587
Max Act: 4.1587. Min Act: -0.1700
Data Index: 3640285 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1587. Min Range: -4.1587
Max Act: 4.0650. Min Act: -0.1700
Data Index: 72164 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.8148. Min Act: -0.1700
Data Index: 4649974 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7836. Min Act: -0.1700
Data Index: 5821687 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7992. Min Act: -0.1700
Data Index: 4599805 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7836. Min Act: -0.1700
Data Index: 8346773 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7054. Min Act: -0.1700
Data Index: 729981 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.6897. Min Act: -0.1700
Data Index: 7799189 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7054. Min Act: -0.1700
Data Index: 7776785 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.6897. Min Act: -0.1700
Data Index: 1443064 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.6741. Min Act: -0.1700
Data Index: 2061854 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.7054. Min Act: -0.1700
Data Index: 6809104 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.6584. Min Act: -0.1700
Data Index: 5745751 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.6428. Min Act: -0.1700
Data Index: 3808280 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5958. Min Act: -0.1700
Data Index: 6189624 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5645. Min Act: -0.1700
Data Index: 6205171 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5645. Min Act: -0.1700
Data Index: 5339578 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5645. Min Act: -0.1700
Data Index: 4904132 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5489. Min Act: -0.1700
Data Index: 5779327 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1587. Min Range: -4.1587
Max Act: 3.5489. Min Act: -0.1700
Data Index: 4872819 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19