Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.7534. Min Act: -0.1700
Data Index: 3711961 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1134383 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.5034. Min Act: -0.1700
Data Index: 1785143 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.4097. Min Act: -0.1700
Data Index: 4866348 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.4097. Min Act: -0.1700
Data Index: 763856 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.3784. Min Act: -0.1700
Data Index: 8092298 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.3784. Min Act: -0.1700
Data Index: 943550 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.3472. Min Act: -0.1700
Data Index: 5994807 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.3472. Min Act: -0.1700
Data Index: 3077046 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.3159. Min Act: -0.1700
Data Index: 2237400 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2534. Min Act: -0.1700
Data Index: 5267016 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2534. Min Act: -0.1700
Data Index: 5995726 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2534. Min Act: -0.1700
Data Index: 1239324 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2222. Min Act: -0.1700
Data Index: 7811133 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2222. Min Act: -0.1700
Data Index: 3669003 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2222. Min Act: -0.1700
Data Index: 7294461 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.2222. Min Act: -0.1700
Data Index: 594026 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.1909. Min Act: -0.1700
Data Index: 7181042 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.1909. Min Act: -0.1700
Data Index: 7626601 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7534. Min Range: -5.7534
Max Act: 5.1909. Min Act: -0.1700
Data Index: 5296983 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19