Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2706. Min Range: -9.2706
Max Act: 9.2706. Min Act: -0.1700
Data Index: 1121717 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2706. Min Range: -9.2706
Max Act: 9.2706. Min Act: -0.1699
Data Index: 7110596 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2706. Min Range: -9.2706
Max Act: 9.1456. Min Act: -0.1700
Data Index: 1123519 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2706. Min Range: -9.2706
Max Act: 9.0831. Min Act: -0.1700
Data Index: 2430186 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.9581. Min Act: -0.1700
Data Index: 3828284 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.7706. Min Act: -0.1700
Data Index: 402542 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.8956. Min Act: -0.1700
Data Index: 2268481 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.7706. Min Act: -0.1700
Data Index: 6884039 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.7706. Min Act: -0.1700
Data Index: 8368276 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.7081. Min Act: -0.1700
Data Index: 7385454 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.7081. Min Act: -0.1700
Data Index: 6177235 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.6456. Min Act: -0.1700
Data Index: 2266310 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.6456. Min Act: -0.1700
Data Index: 5867083 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.5206. Min Act: -0.1700
Data Index: 4954123 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.5206. Min Act: -0.1700
Data Index: 310332 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.5831. Min Act: -0.1700
Data Index: 2776201 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.5206. Min Act: -0.1700
Data Index: 412852 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.5206. Min Act: -0.1700
Data Index: 4649590 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.4581. Min Act: -0.1700
Data Index: 528814 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2706. Min Range: -9.2706
Max Act: 8.4581. Min Act: -0.1700
Data Index: 2585760 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19