Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4708 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.8807. Min Act: -0.1700
Data Index: 2647646 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.6735. Min Act: -0.1700
Data Index: 1875768 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.6092. Min Act: -0.1700
Data Index: 5732772 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5931. Min Act: -0.1700
Data Index: 2400075 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5931. Min Act: -0.1700
Data Index: 6095714 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5931. Min Act: -0.1700
Data Index: 8457223 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5448. Min Act: -0.1700
Data Index: 3089848 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5286. Min Act: -0.1700
Data Index: 2782760 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5286. Min Act: -0.1700
Data Index: 3483827 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5124. Min Act: -0.1700
Data Index: 576726 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5124. Min Act: -0.1700
Data Index: 8530977 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.5124. Min Act: -0.1700
Data Index: 2749970 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4962. Min Act: -0.1700
Data Index: 6707432 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4638. Min Act: -0.1700
Data Index: 3023361 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4800. Min Act: -0.1700
Data Index: 4947878 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4475. Min Act: -0.1700
Data Index: 724500 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4638. Min Act: -0.1700
Data Index: 7170402 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4475. Min Act: -0.1700
Data Index: 4820470 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4638. Min Act: -0.1700
Data Index: 4697503 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8807. Min Range: -2.8807
Max Act: 2.4475. Min Act: -0.1700
Data Index: 8476873 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19