Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.9209. Min Act: -0.1700
Data Index: 1763963 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8583. Min Act: -0.1700
Data Index: 6165719 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8583. Min Act: -0.1700
Data Index: 4625154 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8270. Min Act: -0.1700
Data Index: 7591794 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8270. Min Act: -0.1700
Data Index: 2501056 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8114. Min Act: -0.1700
Data Index: 6173547 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7958. Min Act: -0.1700
Data Index: 8573574 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7958. Min Act: -0.1700
Data Index: 3171665 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7645. Min Act: -0.1700
Data Index: 7776647 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7332. Min Act: -0.1700
Data Index: 2325051 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7332. Min Act: -0.1700
Data Index: 7903310 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7176. Min Act: -0.1700
Data Index: 3054413 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7019. Min Act: -0.1700
Data Index: 5227416 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7176. Min Act: -0.1700
Data Index: 2110013 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6706. Min Act: -0.1700
Data Index: 4883366 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6863. Min Act: -0.1700
Data Index: 137460 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6550. Min Act: -0.1700
Data Index: 1256876 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 6645034 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 1185035 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 4077900 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19