Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.7819. Min Act: -0.1700
Data Index: 7816683 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.7194. Min Act: -0.1700
Data Index: 7816684 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.7194. Min Act: -0.1700
Data Index: 4447547 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.7194. Min Act: -0.1700
Data Index: 1922776 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 2281540 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 590126 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3188294 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 2141785 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 5541961 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 1724178 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 3577158 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 4165875 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5631. Min Act: -0.1700
Data Index: 4799403 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5631. Min Act: -0.1700
Data Index: 6693930 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5631. Min Act: -0.1700
Data Index: 5620719 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5631. Min Act: -0.1700
Data Index: 5144520 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5631. Min Act: -0.1700
Data Index: 6652212 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5319. Min Act: -0.1700
Data Index: 5363240 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5319. Min Act: -0.1700
Data Index: 2484139 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7819. Min Range: -4.7819
Max Act: 4.5319. Min Act: -0.1700
Data Index: 6652214 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19