Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3834 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0072. Min Range: -5.0072
Max Act: 5.0072. Min Act: -0.1700
Data Index: 3995316 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.9447. Min Act: -0.1700
Data Index: 3988090 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.9134. Min Act: -0.1700
Data Index: 8247243 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.8197. Min Act: -0.1700
Data Index: 1647234 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.8197. Min Act: -0.1700
Data Index: 3069343 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6947. Min Act: -0.1700
Data Index: 8073555 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.7259. Min Act: -0.1700
Data Index: 8487625 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6947. Min Act: -0.1700
Data Index: 1711055 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6634. Min Act: -0.1700
Data Index: 2773177 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6634. Min Act: -0.1700
Data Index: 5327100 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6634. Min Act: -0.1700
Data Index: 7260882 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6634. Min Act: -0.1700
Data Index: 4511519 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 5124489 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6322. Min Act: -0.1700
Data Index: 7420002 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 3234612 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 7478050 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 783678 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 7022741 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.5697. Min Act: -0.1700
Data Index: 7285054 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0072. Min Range: -5.0072
Max Act: 4.6009. Min Act: -0.1700
Data Index: 3101657 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19