Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.8161. Min Act: -0.1700
Data Index: 2971751 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7536. Min Act: -0.1700
Data Index: 2971752 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7849. Min Act: -0.1700
Data Index: 3994402 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6599. Min Act: -0.1700
Data Index: 5980662 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6599. Min Act: -0.1700
Data Index: 1234440 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 944036 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 6194009 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 6280723 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 201273 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 281220 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 5644 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 2726512 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 6797262 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 4238306 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 1387357 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 4251972 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 4837171 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 3915491 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 3464949 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 6711762 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19