Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.6946. Min Act: -0.1700
Data Index: 327040 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.5071. Min Act: -0.1700
Data Index: 2637974 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.4446. Min Act: -0.1700
Data Index: 6707378 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.4134. Min Act: -0.1700
Data Index: 3802107 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3821. Min Act: -0.1700
Data Index: 4697732 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3509. Min Act: -0.1700
Data Index: 3781013 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3821. Min Act: -0.1700
Data Index: 883553 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4946736 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3509. Min Act: -0.1700
Data Index: 7791473 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3196. Min Act: -0.1700
Data Index: 6432219 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.3196. Min Act: -0.1700
Data Index: 7944739 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2884. Min Act: -0.1700
Data Index: 6792758 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3407265 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2571. Min Act: -0.1700
Data Index: 5187602 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2259. Min Act: -0.1700
Data Index: 6768887 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2259. Min Act: -0.1700
Data Index: 5702760 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2259. Min Act: -0.1700
Data Index: 1387354 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2259. Min Act: -0.1700
Data Index: 6515162 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.2259. Min Act: -0.1700
Data Index: 1607535 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6946. Min Range: -5.6946
Max Act: 5.1946. Min Act: -0.1700
Data Index: 1224090 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19