Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0287. Min Range: -3.0287
Max Act: 3.0287. Min Act: -0.1700
Data Index: 2787581 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9338. Min Act: -0.1700
Data Index: 4121636 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9338. Min Act: -0.1700
Data Index: 6509582 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9338. Min Act: -0.1700
Data Index: 7117778 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9180. Min Act: -0.1700
Data Index: 6872532 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9180. Min Act: -0.1700
Data Index: 2722873 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9180. Min Act: -0.1700
Data Index: 4830143 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8862. Min Act: -0.1700
Data Index: 3703087 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.9021. Min Act: -0.1700
Data Index: 3473970 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8545. Min Act: -0.1700
Data Index: 4982839 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8704. Min Act: -0.1700
Data Index: 4701179 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8545. Min Act: -0.1700
Data Index: 3607089 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8545. Min Act: -0.1700
Data Index: 1807328 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8704. Min Act: -0.1700
Data Index: 8222738 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8227. Min Act: -0.1700
Data Index: 4238102 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8227. Min Act: -0.1700
Data Index: 1123619 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8386. Min Act: -0.1700
Data Index: 4977189 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8545. Min Act: -0.1700
Data Index: 589516 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8386. Min Act: -0.1700
Data Index: 1956938 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0287. Min Range: -3.0287
Max Act: 2.8227. Min Act: -0.1700
Data Index: 3990628 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19