Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0015. Min Range: -4.0015
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1225630 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.9858. Min Act: -0.1700
Data Index: 5236470 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.9233. Min Act: -0.1700
Data Index: 5451048 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8764. Min Act: -0.1700
Data Index: 6416030 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8608. Min Act: -0.1700
Data Index: 7327673 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8451. Min Act: -0.1700
Data Index: 637426 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8451. Min Act: -0.1700
Data Index: 7478096 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8139. Min Act: -0.1700
Data Index: 5750156 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.8139. Min Act: -0.1700
Data Index: 496522 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7982. Min Act: -0.1700
Data Index: 8676707 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7826. Min Act: -0.1700
Data Index: 2337088 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7826. Min Act: -0.1700
Data Index: 6185435 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7982. Min Act: -0.1700
Data Index: 764702 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7982. Min Act: -0.1700
Data Index: 7674293 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7826. Min Act: -0.1700
Data Index: 5667029 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7982. Min Act: -0.1700
Data Index: 8578326 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7670. Min Act: -0.1700
Data Index: 6345616 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7670. Min Act: -0.1700
Data Index: 8778062 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7513. Min Act: -0.1700
Data Index: 8175312 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0015. Min Range: -4.0015
Max Act: 3.7513. Min Act: -0.1700
Data Index: 4021940 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19