Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.4735. Min Act: -0.1700
Data Index: 168365 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.3485. Min Act: -0.1700
Data Index: 4449577 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 168366 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 3905742 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.2547. Min Act: -0.1700
Data Index: 7332711 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 4473386 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 2041930 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 4370556 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.2235. Min Act: -0.1700
Data Index: 3931141 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 4990348 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6443774 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1922. Min Act: -0.1700
Data Index: 1350425 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1609. Min Act: -0.1700
Data Index: 7215736 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1297. Min Act: -0.1700
Data Index: 321334 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.0984. Min Act: -0.1700
Data Index: 8484495 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1297. Min Act: -0.1700
Data Index: 433117 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1297. Min Act: -0.1700
Data Index: 4262380 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.1297. Min Act: -0.1700
Data Index: 6714499 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.0984. Min Act: -0.1700
Data Index: 8187459 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4735. Min Range: -4.4735
Max Act: 4.0984. Min Act: -0.1700
Data Index: 6753272 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19