Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3124. Min Range: -9.3124
Max Act: 9.3124. Min Act: -0.1700
Data Index: 4184763 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.9999. Min Act: -0.1700
Data Index: 8701234 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.8749. Min Act: -0.1700
Data Index: 4184764 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.8749. Min Act: -0.1700
Data Index: 7896065 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.8124. Min Act: -0.1700
Data Index: 1681127 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.7499. Min Act: -0.1700
Data Index: 1278620 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.6874. Min Act: -0.1700
Data Index: 4050170 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.6874. Min Act: -0.1700
Data Index: 7477612 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.6249. Min Act: -0.1700
Data Index: 7949393 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.6249. Min Act: -0.1700
Data Index: 7494377 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4999. Min Act: -0.1700
Data Index: 6249402 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4999. Min Act: -0.1700
Data Index: 7613574 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4374. Min Act: -0.1699
Data Index: 5829631 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4374. Min Act: -0.1700
Data Index: 1874423 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4374. Min Act: -0.1700
Data Index: 6864701 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.4374. Min Act: -0.1700
Data Index: 6748830 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.3749. Min Act: -0.1700
Data Index: 7026439 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.3749. Min Act: -0.1700
Data Index: 521525 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.3749. Min Act: -0.1700
Data Index: 3654578 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3124. Min Range: -9.3124
Max Act: 8.3749. Min Act: -0.1700
Data Index: 4286642 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19