Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.4944. Min Act: -0.1700
Data Index: 7588749 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.4006. Min Act: -0.1700
Data Index: 2546996 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1819. Min Act: -0.1700
Data Index: 4741536 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.2131. Min Act: -0.1700
Data Index: 8745607 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1819. Min Act: -0.1700
Data Index: 8695570 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1819. Min Act: -0.1700
Data Index: 1426819 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1819. Min Act: -0.1700
Data Index: 5454638 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1506. Min Act: -0.1700
Data Index: 1031417 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1194. Min Act: -0.1700
Data Index: 1031418 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1506. Min Act: -0.1700
Data Index: 6996781 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1506. Min Act: -0.1700
Data Index: 2815600 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1194. Min Act: -0.1700
Data Index: 3579907 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.1194. Min Act: -0.1700
Data Index: 2132315 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0881. Min Act: -0.1700
Data Index: 4960838 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0881. Min Act: -0.1700
Data Index: 3126693 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0881. Min Act: -0.1700
Data Index: 6943395 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0881. Min Act: -0.1700
Data Index: 6133950 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0881. Min Act: -0.1700
Data Index: 1601887 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0569. Min Act: -0.1700
Data Index: 6927170 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4944. Min Range: -6.4944
Max Act: 6.0569. Min Act: -0.1700
Data Index: 1426818 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19