Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.6095. Min Act: -0.1700
Data Index: 6945642 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.5626. Min Act: -0.1700
Data Index: 5934840 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4999. Min Act: -0.1700
Data Index: 789183 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4843. Min Act: -0.1700
Data Index: 3550129 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4843. Min Act: -0.1700
Data Index: 7541195 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4686. Min Act: -0.1700
Data Index: 6945641 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4216. Min Act: -0.1700
Data Index: 7085124 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4373. Min Act: -0.1700
Data Index: 4018748 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4529. Min Act: -0.1700
Data Index: 8606273 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4843. Min Act: -0.1700
Data Index: 4659284 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4373. Min Act: -0.1700
Data Index: 4974466 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4216. Min Act: -0.1700
Data Index: 6955606 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4216. Min Act: -0.1700
Data Index: 3880084 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4059. Min Act: -0.1700
Data Index: 5674611 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4216. Min Act: -0.1700
Data Index: 6548985 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.3902. Min Act: -0.1700
Data Index: 7201830 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4059. Min Act: -0.1700
Data Index: 7089757 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4059. Min Act: -0.1700
Data Index: 7752472 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4059. Min Act: -0.1700
Data Index: 865414 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6095. Min Range: -3.6095
Max Act: 3.4059. Min Act: -0.1700
Data Index: 2033719 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19