Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.4171. Min Act: -0.1700
Data Index: 1933157 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.1983. Min Act: -0.1700
Data Index: 2734149 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.2296. Min Act: -0.1700
Data Index: 2713432 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.1671. Min Act: -0.1700
Data Index: 3471655 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.1358. Min Act: -0.1700
Data Index: 2372847 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1051342 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4171. Min Range: -7.4171
Max Act: 7.0733. Min Act: -0.1700
Data Index: 3417193 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.9796. Min Act: -0.1700
Data Index: 5576476 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.9483. Min Act: -0.1700
Data Index: 370599 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.9483. Min Act: -0.1700
Data Index: 5086929 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.9171. Min Act: -0.1700
Data Index: 8768309 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.9171. Min Act: -0.1700
Data Index: 4981667 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.7608. Min Act: -0.1700
Data Index: 4784551 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.7608. Min Act: -0.1700
Data Index: 8415467 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.7608. Min Act: -0.1700
Data Index: 6853618 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.7608. Min Act: -0.1700
Data Index: 5141230 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.7608. Min Act: -0.1700
Data Index: 663138 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.6983. Min Act: -0.1700
Data Index: 6900787 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.6983. Min Act: -0.1700
Data Index: 8571042 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4171. Min Range: -7.4171
Max Act: 6.6671. Min Act: -0.1700
Data Index: 3052983 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19