Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.4089. Min Act: -0.1700
Data Index: 6943256 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6943254 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 8699746 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.1277. Min Act: -0.1700
Data Index: 8561061 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.1277. Min Act: -0.1700
Data Index: 1798968 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.0027. Min Act: -0.1700
Data Index: 8286753 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4089. Min Range: -6.4089
Max Act: 6.0027. Min Act: -0.1700
Data Index: 6519675 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.9402. Min Act: -0.1700
Data Index: 8376887 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.9089. Min Act: -0.1700
Data Index: 7485950 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.9402. Min Act: -0.1700
Data Index: 339487 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8464. Min Act: -0.1700
Data Index: 6240160 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8777. Min Act: -0.1700
Data Index: 5173929 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8777. Min Act: -0.1700
Data Index: 8644818 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8777. Min Act: -0.1700
Data Index: 770196 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8777. Min Act: -0.1700
Data Index: 3968448 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8152. Min Act: -0.1700
Data Index: 1112599 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.7839. Min Act: -0.1700
Data Index: 5918956 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.7839. Min Act: -0.1700
Data Index: 5807499 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.7839. Min Act: -0.1700
Data Index: 340646 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4089. Min Range: -6.4089
Max Act: 5.8152. Min Act: -0.1700
Data Index: 2270012 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19