Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.6612. Min Act: -0.1700
Data Index: 5083091 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.6452. Min Act: -0.1700
Data Index: 1782413 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.6291. Min Act: -0.1700
Data Index: 6128852 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.6131. Min Act: -0.1700
Data Index: 5083096 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.5647. Min Act: -0.1700
Data Index: 5083095 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.5325. Min Act: -0.1700
Data Index: 5378561 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.5001. Min Act: -0.1700
Data Index: 8055587 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.5163. Min Act: -0.1700
Data Index: 6894116 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4839. Min Act: -0.1700
Data Index: 3473189 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4839. Min Act: -0.1700
Data Index: 3340691 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4514. Min Act: -0.1700
Data Index: 2281047 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4514. Min Act: -0.1700
Data Index: 637046 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4351. Min Act: -0.1700
Data Index: 8156845 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4351. Min Act: -0.1700
Data Index: 2576357 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4188. Min Act: -0.1700
Data Index: 4883140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4351. Min Act: -0.1700
Data Index: 5083092 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4351. Min Act: -0.1700
Data Index: 3981823 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4188. Min Act: -0.1700
Data Index: 7512095 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4188. Min Act: -0.1700
Data Index: 2372878 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6612. Min Range: -2.6612
Max Act: 2.4188. Min Act: -0.1700
Data Index: 6474926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19