Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0053. Min Range: -4.0053
Max Act: 4.0053. Min Act: -0.1700
Data Index: 4415847 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.9740. Min Act: -0.1700
Data Index: 8830637 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6766570 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8803. Min Act: -0.1700
Data Index: 5261592 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8803. Min Act: -0.1700
Data Index: 90873 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6067378 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8490. Min Act: -0.1700
Data Index: 8116391 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8490. Min Act: -0.1700
Data Index: 180619 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8177. Min Act: -0.1700
Data Index: 7709001 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8177. Min Act: -0.1700
Data Index: 7367587 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8177. Min Act: -0.1700
Data Index: 2433751 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7552. Min Act: -0.1700
Data Index: 8344576 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7864. Min Act: -0.1700
Data Index: 2292754 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.8177. Min Act: -0.1700
Data Index: 5935700 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7864. Min Act: -0.1700
Data Index: 7616587 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7864. Min Act: -0.1700
Data Index: 7191617 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7864. Min Act: -0.1700
Data Index: 1829885 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7864. Min Act: -0.1700
Data Index: 3589527 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7552. Min Act: -0.1700
Data Index: 562821 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0053. Min Range: -4.0053
Max Act: 3.7552. Min Act: -0.1700
Data Index: 5761337 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19