Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.6761. Min Act: -0.1700
Data Index: 345723 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.6449. Min Act: -0.1700
Data Index: 5410571 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.6136. Min Act: -0.1700
Data Index: 4525732 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.5199. Min Act: -0.1700
Data Index: 219620 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.4886. Min Act: -0.1700
Data Index: 3616165 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.4574. Min Act: -0.1700
Data Index: 2893254 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.4261. Min Act: -0.1700
Data Index: 3081140 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.4261. Min Act: -0.1700
Data Index: 8743731 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3949. Min Act: -0.1700
Data Index: 3946120 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3949. Min Act: -0.1700
Data Index: 6107118 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.4261. Min Act: -0.1700
Data Index: 3488008 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3636. Min Act: -0.1700
Data Index: 8697821 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3636. Min Act: -0.1700
Data Index: 8205167 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3636. Min Act: -0.1700
Data Index: 6243521 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3324. Min Act: -0.1700
Data Index: 7820305 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3324. Min Act: -0.1700
Data Index: 1515824 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3324. Min Act: -0.1700
Data Index: 3806371 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3011. Min Act: -0.1700
Data Index: 3952012 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3011. Min Act: -0.1700
Data Index: 5217994 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6761. Min Range: -5.6761
Max Act: 5.3011. Min Act: -0.1700
Data Index: 2618568 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19