Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2160. Min Range: -6.2160
Max Act: 6.2160. Min Act: -0.1700
Data Index: 6753546 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2160. Min Range: -6.2160
Max Act: 6.0597. Min Act: -0.1700
Data Index: 1690216 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.9347. Min Act: -0.1700
Data Index: 158369 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.9347. Min Act: -0.1700
Data Index: 523527 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.9035. Min Act: -0.1700
Data Index: 840927 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8722. Min Act: -0.1700
Data Index: 5688232 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8722. Min Act: -0.1700
Data Index: 5135851 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8410. Min Act: -0.1700
Data Index: 8624989 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4215125 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8410. Min Act: -0.1700
Data Index: 6406064 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8722. Min Act: -0.1700
Data Index: 3469436 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7785. Min Act: -0.1700
Data Index: 1366584 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6051304 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6715319 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7472. Min Act: -0.1700
Data Index: 612045 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7472. Min Act: -0.1700
Data Index: 5642173 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7472. Min Act: -0.1700
Data Index: 3989485 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3177274 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3018207 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2160. Min Range: -6.2160
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5716357 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19