Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.3525. Min Act: -0.1700
Data Index: 6682883 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.3361. Min Act: -0.1700
Data Index: 2111778 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2868. Min Act: -0.1700
Data Index: 6347164 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2868. Min Act: -0.1700
Data Index: 629016 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2868. Min Act: -0.1700
Data Index: 4452451 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2868. Min Act: -0.1700
Data Index: 5511578 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2703. Min Act: -0.1700
Data Index: 3587396 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2538. Min Act: -0.1700
Data Index: 4967925 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2538. Min Act: -0.1700
Data Index: 5411345 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2207. Min Act: -0.1700
Data Index: 366290 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2207. Min Act: -0.1700
Data Index: 8514279 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2207. Min Act: -0.1700
Data Index: 304208 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2041. Min Act: -0.1700
Data Index: 6433121 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2041. Min Act: -0.1700
Data Index: 4766475 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.1875. Min Act: -0.1700
Data Index: 968751 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.1875. Min Act: -0.1700
Data Index: 4759838 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2041. Min Act: -0.1700
Data Index: 223235 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.2041. Min Act: -0.1700
Data Index: 3094950 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.1709. Min Act: -0.1700
Data Index: 2194249 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3525. Min Range: -2.3525
Max Act: 2.1875. Min Act: -0.1700
Data Index: 4686943 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19