Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6972. Min Act: -0.1700
Data Index: 3556768 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1729225 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6660. Min Act: -0.1700
Data Index: 6043057 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6972. Min Act: -0.1700
Data Index: 7419174 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6347. Min Act: -0.1700
Data Index: 7123180 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6347. Min Act: -0.1700
Data Index: 7666009 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6347. Min Act: -0.1700
Data Index: 918724 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6660. Min Act: -0.1700
Data Index: 5787175 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6035. Min Act: -0.1700
Data Index: 147763 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.6035. Min Act: -0.1700
Data Index: 2719067 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5722. Min Act: -0.1700
Data Index: 7491073 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5722. Min Act: -0.1700
Data Index: 6729427 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2142167 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2187255 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.4785. Min Act: -0.1700
Data Index: 8172682 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5097. Min Act: -0.1700
Data Index: 2872061 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.4785. Min Act: -0.1700
Data Index: 7697231 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5097. Min Act: -0.1700
Data Index: 279223 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5097. Min Act: -0.1700
Data Index: 1559480 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6972. Min Range: -4.6972
Max Act: 4.5097. Min Act: -0.1700
Data Index: 4543012 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19