Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4676. Min Range: -8.4676
Max Act: 8.4676. Min Act: -0.1700
Data Index: 5185193 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4676. Min Range: -8.4676
Max Act: 8.0301. Min Act: -0.1700
Data Index: 8224895 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.9676. Min Act: -0.1700
Data Index: 5422003 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.9676. Min Act: -0.1700
Data Index: 1585938 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.9676. Min Act: -0.1700
Data Index: 1493700 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.9676. Min Act: -0.1700
Data Index: 2059533 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.8113. Min Act: -0.1700
Data Index: 8080232 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.7801. Min Act: -0.1700
Data Index: 213346 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.6863. Min Act: -0.1700
Data Index: 4861329 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.7176. Min Act: -0.1700
Data Index: 440170 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.6551. Min Act: -0.1700
Data Index: 6806027 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.6238. Min Act: -0.1700
Data Index: 4703726 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.6238. Min Act: -0.1700
Data Index: 6473738 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.5926. Min Act: -0.1700
Data Index: 6119617 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.5613. Min Act: -0.1700
Data Index: 2553602 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.4988. Min Act: -0.1700
Data Index: 958861 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.4988. Min Act: -0.1700
Data Index: 3032275 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.4988. Min Act: -0.1700
Data Index: 1212012 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.4988. Min Act: -0.1700
Data Index: 2985150 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4676. Min Range: -8.4676
Max Act: 7.4676. Min Act: -0.1700
Data Index: 507818 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19