Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.6895. Min Act: -0.1700
Data Index: 5942081 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.5645. Min Act: -0.1700
Data Index: 1081143 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.5333. Min Act: -0.1700
Data Index: 4177874 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.5020. Min Act: -0.1700
Data Index: 4648871 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4708. Min Act: -0.1700
Data Index: 486481 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4708. Min Act: -0.1700
Data Index: 7120355 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4708. Min Act: -0.1700
Data Index: 2884608 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6260806 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6291676 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4083. Min Act: -0.1700
Data Index: 1081144 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.4083. Min Act: -0.1700
Data Index: 8641887 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.3770. Min Act: -0.1700
Data Index: 2112677 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.3770. Min Act: -0.1700
Data Index: 2454473 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.3145. Min Act: -0.1700
Data Index: 4679860 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.3458. Min Act: -0.1700
Data Index: 2454474 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.3145. Min Act: -0.1700
Data Index: 1001084 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.2833. Min Act: -0.1700
Data Index: 1081140 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.2833. Min Act: -0.1700
Data Index: 8493946 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.2833. Min Act: -0.1700
Data Index: 4679850 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6895. Min Range: -5.6895
Max Act: 5.2833. Min Act: -0.1700
Data Index: 1625074 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19