Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.5095. Min Act: -0.1700
Data Index: 1527780 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.5095. Min Act: -0.1700
Data Index: 6705976 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3845. Min Act: -0.1700
Data Index: 5446219 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3532. Min Act: -0.1700
Data Index: 1536755 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3532. Min Act: -0.1700
Data Index: 6442090 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3220. Min Act: -0.1700
Data Index: 4973671 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3220. Min Act: -0.1700
Data Index: 1990765 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3220. Min Act: -0.1700
Data Index: 6465285 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.3220. Min Act: -0.1700
Data Index: 3682538 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2907. Min Act: -0.1700
Data Index: 7133087 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2907. Min Act: -0.1700
Data Index: 2735646 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2907. Min Act: -0.1700
Data Index: 5116368 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2907. Min Act: -0.1700
Data Index: 253541 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2282. Min Act: -0.1700
Data Index: 7740021 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2595. Min Act: -0.1700
Data Index: 5160187 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2595. Min Act: -0.1700
Data Index: 3331294 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2282. Min Act: -0.1700
Data Index: 6211964 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.1970. Min Act: -0.1700
Data Index: 5455518 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2595. Min Act: -0.1700
Data Index: 2869171 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5095. Min Range: -4.5095
Max Act: 4.2282. Min Act: -0.1700
Data Index: 5217932 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19