Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0750. Min Range: -6.0750
Max Act: 6.0750. Min Act: -0.1700
Data Index: 1784167 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.9500. Min Act: -0.1700
Data Index: 377846 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.9187. Min Act: -0.1700
Data Index: 457965 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.8562. Min Act: -0.1700
Data Index: 1215628 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.8250. Min Act: -0.1700
Data Index: 3913708 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.7312. Min Act: -0.1700
Data Index: 4144948 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.6687. Min Act: -0.1700
Data Index: 3556603 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.6375. Min Act: -0.1700
Data Index: 3205394 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.6062. Min Act: -0.1700
Data Index: 5683594 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5750. Min Act: -0.1700
Data Index: 986602 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4265952 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5750. Min Act: -0.1700
Data Index: 5419455 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5437. Min Act: -0.1700
Data Index: 6726239 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5437. Min Act: -0.1700
Data Index: 34838 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5125. Min Act: -0.1700
Data Index: 1475005 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5125. Min Act: -0.1700
Data Index: 5670135 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5125. Min Act: -0.1700
Data Index: 1262096 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5437. Min Act: -0.1700
Data Index: 6060090 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.4812. Min Act: -0.1700
Data Index: 2509119 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0750. Min Range: -6.0750
Max Act: 5.5125. Min Act: -0.1700
Data Index: 6961583 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19