Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.4637. Min Act: -0.1685
Data Index: 3853267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.4475. Min Act: -0.1578
Data Index: 7464214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.4312. Min Act: -0.1695
Data Index: 535542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3986. Min Act: -0.1475
Data Index: 3018312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3986. Min Act: -0.1312
Data Index: 996040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3986. Min Act: -0.1456
Data Index: 6405829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3823. Min Act: -0.1475
Data Index: 6770705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3823. Min Act: -0.1414
Data Index: 6586541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3495. Min Act: -0.1573
Data Index: 3772215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1488
Data Index: 6751909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1400
Data Index: 852322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3495. Min Act: -0.1442
Data Index: 3307950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3495. Min Act: -0.1511
Data Index: 3724244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3495. Min Act: -0.1407
Data Index: 8629741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3495. Min Act: -0.1582
Data Index: 4942677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1648
Data Index: 7270912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1506
Data Index: 8660409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1369
Data Index: 5184102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3167. Min Act: -0.1377
Data Index: 1340537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4637. Min Range: -2.4637
Max Act: 2.3331. Min Act: -0.1500
Data Index: 7662794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19