Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2442 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3049. Min Range: -7.3049
Max Act: 7.3049. Min Act: -0.1700
Data Index: 4209419 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.9924. Min Act: -0.1700
Data Index: 7207940 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4733399 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.9299. Min Act: -0.1700
Data Index: 7095745 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.8674. Min Act: -0.1700
Data Index: 6669869 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.8987. Min Act: -0.1700
Data Index: 1296878 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.8362. Min Act: -0.1700
Data Index: 5362002 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7737. Min Act: -0.1700
Data Index: 4516751 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7424. Min Act: -0.1700
Data Index: 8112579 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7424. Min Act: -0.1700
Data Index: 5007844 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7112. Min Act: -0.1700
Data Index: 544680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7112. Min Act: -0.1700
Data Index: 4408269 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.7112. Min Act: -0.1700
Data Index: 8516436 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6799. Min Act: -0.1700
Data Index: 3908150 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6799. Min Act: -0.1700
Data Index: 1444363 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6799. Min Act: -0.1700
Data Index: 5158305 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6799. Min Act: -0.1700
Data Index: 2079204 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6487. Min Act: -0.1700
Data Index: 8359739 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6487. Min Act: -0.1700
Data Index: 3925247 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3049. Min Range: -7.3049
Max Act: 6.6487. Min Act: -0.1700
Data Index: 2853130 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19