Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.4080. Min Act: -0.1700
Data Index: 589138 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.4393. Min Act: -0.1700
Data Index: 2636568 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.3455. Min Act: -0.1700
Data Index: 32523 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.3143. Min Act: -0.1700
Data Index: 2269106 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.2830. Min Act: -0.1700
Data Index: 5586487 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.2830. Min Act: -0.1700
Data Index: 1468361 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.2205. Min Act: -0.1700
Data Index: 786005 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.1893. Min Act: -0.1700
Data Index: 2281929 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.1268. Min Act: -0.1700
Data Index: 4933501 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0955. Min Act: -0.1700
Data Index: 7041272 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.1268. Min Act: -0.1700
Data Index: 7453681 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0955. Min Act: -0.1700
Data Index: 4990000 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0955. Min Act: -0.1700
Data Index: 5882286 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0955. Min Act: -0.1700
Data Index: 5123819 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0643. Min Act: -0.1700
Data Index: 8323391 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0955. Min Act: -0.1700
Data Index: 678582 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0330. Min Act: -0.1700
Data Index: 7184177 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0330. Min Act: -0.1700
Data Index: 7000621 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0330. Min Act: -0.1700
Data Index: 1182182 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4393. Min Range: -7.4393
Max Act: 7.0330. Min Act: -0.1700
Data Index: 1124041 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19