Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.5329. Min Act: -0.1700
Data Index: 8827898 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.5172. Min Act: -0.1700
Data Index: 5180624 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.5329. Min Act: -0.1700
Data Index: 6083202 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4702. Min Act: -0.1700
Data Index: 745340 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4545. Min Act: -0.1700
Data Index: 16222 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4389. Min Act: -0.1700
Data Index: 8691234 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4389. Min Act: -0.1700
Data Index: 1334620 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4545. Min Act: -0.1700
Data Index: 2650244 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4545. Min Act: -0.1700
Data Index: 1520835 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4545. Min Act: -0.1700
Data Index: 1176764 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4389. Min Act: -0.1700
Data Index: 2906684 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4389. Min Act: -0.1700
Data Index: 6893175 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4075. Min Act: -0.1700
Data Index: 2074615 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4232. Min Act: -0.1700
Data Index: 4154447 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4075. Min Act: -0.1700
Data Index: 1000548 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.3918. Min Act: -0.1700
Data Index: 8318274 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4075. Min Act: -0.1700
Data Index: 6854995 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.3918. Min Act: -0.1700
Data Index: 6557028 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.3918. Min Act: -0.1700
Data Index: 5704602 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5329. Min Range: -3.5329
Max Act: 3.4075. Min Act: -0.1700
Data Index: 3536868 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19