Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.1226. Min Act: -0.1700
Data Index: 3578618 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.0279. Min Act: -0.1700
Data Index: 2708630 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.0279. Min Act: -0.1700
Data Index: 6808456 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.0121. Min Act: -0.1700
Data Index: 7270235 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.0437. Min Act: -0.1700
Data Index: 7482821 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1226. Min Range: -3.1226
Max Act: 3.0279. Min Act: -0.1700
Data Index: 2255023 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9963. Min Act: -0.1700
Data Index: 4064108 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9647. Min Act: -0.1700
Data Index: 1579095 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9331. Min Act: -0.1700
Data Index: 3157449 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9489. Min Act: -0.1700
Data Index: 2175886 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9331. Min Act: -0.1700
Data Index: 5026457 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9331. Min Act: -0.1700
Data Index: 8166420 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9172. Min Act: -0.1700
Data Index: 6820822 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9331. Min Act: -0.1700
Data Index: 2368473 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9014. Min Act: -0.1700
Data Index: 6610831 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9172. Min Act: -0.1700
Data Index: 1853977 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9172. Min Act: -0.1700
Data Index: 1926551 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9331. Min Act: -0.1700
Data Index: 7374082 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.9172. Min Act: -0.1700
Data Index: 6930244 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1226. Min Range: -3.1226
Max Act: 2.8855. Min Act: -0.1700
Data Index: 7473980 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19