Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4787. Min Range: -7.4787
Max Act: 7.4787. Min Act: -0.1700
Data Index: 633303 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4787. Min Range: -7.4787
Max Act: 7.4787. Min Act: -0.1700
Data Index: 6365333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4787. Min Range: -7.4787
Max Act: 7.2912. Min Act: -0.1700
Data Index: 6678519 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4787. Min Range: -7.4787
Max Act: 7.1974. Min Act: -0.1700
Data Index: 2991014 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4787. Min Range: -7.4787
Max Act: 7.0099. Min Act: -0.1700
Data Index: 576610 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.9787. Min Act: -0.1700
Data Index: 8541123 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.9162. Min Act: -0.1700
Data Index: 8534248 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.9162. Min Act: -0.1700
Data Index: 6165010 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.8849. Min Act: -0.1700
Data Index: 5439208 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.8224. Min Act: -0.1700
Data Index: 2122171 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.8537. Min Act: -0.1700
Data Index: 8367598 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.8537. Min Act: -0.1700
Data Index: 98123 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.8224. Min Act: -0.1700
Data Index: 8198358 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7912. Min Act: -0.1700
Data Index: 7103507 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7912. Min Act: -0.1700
Data Index: 2347169 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7599. Min Act: -0.1700
Data Index: 4796812 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7287. Min Act: -0.1700
Data Index: 7103505 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7599. Min Act: -0.1700
Data Index: 1137281 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7287. Min Act: -0.1700
Data Index: 5928422 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4787. Min Range: -7.4787
Max Act: 6.7287. Min Act: -0.1700
Data Index: 7828234 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19