Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4062. Min Range: -5.4062
Max Act: 5.4062. Min Act: -0.1700
Data Index: 978732 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4062. Min Range: -5.4062
Max Act: 5.2500. Min Act: -0.1700
Data Index: 1364281 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4062. Min Range: -5.4062
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8186405 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4062. Min Range: -5.4062
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1038178 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4062. Min Range: -5.4062
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8017575 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9687. Min Act: -0.1700
Data Index: 7093161 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9375. Min Act: -0.1700
Data Index: 970375 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9375. Min Act: -0.1700
Data Index: 2283473 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9375. Min Act: -0.1700
Data Index: 164984 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9687. Min Act: -0.1700
Data Index: 7116095 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8750. Min Act: -0.1700
Data Index: 3039720 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9062. Min Act: -0.1700
Data Index: 1681250 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.9062. Min Act: -0.1700
Data Index: 8415996 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8750. Min Act: -0.1700
Data Index: 3173999 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8750. Min Act: -0.1700
Data Index: 5167138 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8437. Min Act: -0.1700
Data Index: 4769154 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8437. Min Act: -0.1700
Data Index: 5513215 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8437. Min Act: -0.1700
Data Index: 1201588 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8125. Min Act: -0.1700
Data Index: 990280 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4062. Min Range: -5.4062
Max Act: 4.8125. Min Act: -0.1700
Data Index: 5999917 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19