Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2205. Min Range: -6.2205
Max Act: 6.2205. Min Act: -0.1700
Data Index: 2357476 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2205. Min Range: -6.2205
Max Act: 6.0643. Min Act: -0.1700
Data Index: 1806367 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2205. Min Range: -6.2205
Max Act: 6.0330. Min Act: -0.1700
Data Index: 5021586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.9080. Min Act: -0.1700
Data Index: 1818831 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.8768. Min Act: -0.1700
Data Index: 2676709 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.8455. Min Act: -0.1700
Data Index: 2285429 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.8143. Min Act: -0.1700
Data Index: 5021585 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.8143. Min Act: -0.1700
Data Index: 5021583 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7830. Min Act: -0.1700
Data Index: 7474842 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7518. Min Act: -0.1700
Data Index: 8366177 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7518. Min Act: -0.1700
Data Index: 8813987 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7518. Min Act: -0.1700
Data Index: 761387 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5794310 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7205. Min Act: -0.1700
Data Index: 162885 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.6893. Min Act: -0.1700
Data Index: 1002061 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.7205. Min Act: -0.1700
Data Index: 8643503 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.6893. Min Act: -0.1700
Data Index: 6607920 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.6893. Min Act: -0.1700
Data Index: 6729475 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.6893. Min Act: -0.1700
Data Index: 6875854 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2205. Min Range: -6.2205
Max Act: 5.6893. Min Act: -0.1700
Data Index: 651027 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19