Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4432. Min Range: -7.4432
Max Act: 7.4432. Min Act: -0.1700
Data Index: 5373039 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4432. Min Range: -7.4432
Max Act: 7.1932. Min Act: -0.1700
Data Index: 4261265 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4432. Min Range: -7.4432
Max Act: 7.0682. Min Act: -0.1700
Data Index: 3265698 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4432. Min Range: -7.4432
Max Act: 7.0682. Min Act: -0.1700
Data Index: 4538209 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.9432. Min Act: -0.1700
Data Index: 6905318 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8807. Min Act: -0.1700
Data Index: 8188647 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8495. Min Act: -0.1700
Data Index: 3144556 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8495. Min Act: -0.1700
Data Index: 4045531 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8495. Min Act: -0.1700
Data Index: 1117096 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8495. Min Act: -0.1700
Data Index: 4422452 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.8182. Min Act: -0.1700
Data Index: 3615933 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7870. Min Act: -0.1700
Data Index: 6620765 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7870. Min Act: -0.1700
Data Index: 5819639 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7557. Min Act: -0.1700
Data Index: 6076485 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7557. Min Act: -0.1700
Data Index: 7285961 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7245. Min Act: -0.1700
Data Index: 5903245 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7245. Min Act: -0.1700
Data Index: 5744023 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.7557. Min Act: -0.1700
Data Index: 2998529 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.6932. Min Act: -0.1700
Data Index: 1873076 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4432. Min Range: -7.4432
Max Act: 6.6932. Min Act: -0.1700
Data Index: 5744022 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19