Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.5869. Min Act: -0.1700
Data Index: 8656364 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.5869. Min Act: -0.1700
Data Index: 7326034 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.3057. Min Act: -0.1700
Data Index: 4125615 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.2119. Min Act: -0.1700
Data Index: 1153168 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.1807. Min Act: -0.1700
Data Index: 4424294 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.1494. Min Act: -0.1700
Data Index: 3013976 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.1807. Min Act: -0.1700
Data Index: 2816664 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.0557. Min Act: -0.1700
Data Index: 3864308 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.0557. Min Act: -0.1700
Data Index: 3774072 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.0244. Min Act: -0.1700
Data Index: 1488329 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5869. Min Range: -7.5869
Max Act: 7.0244. Min Act: -0.1700
Data Index: 872413 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.9307. Min Act: -0.1700
Data Index: 6573102 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8994. Min Act: -0.1700
Data Index: 8536015 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.9307. Min Act: -0.1700
Data Index: 2809824 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8994. Min Act: -0.1700
Data Index: 611551 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8682. Min Act: -0.1700
Data Index: 5396727 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8682. Min Act: -0.1700
Data Index: 3074254 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8369. Min Act: -0.1700
Data Index: 4411125 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8369. Min Act: -0.1700
Data Index: 2801824 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5869. Min Range: -7.5869
Max Act: 6.8369. Min Act: -0.1700
Data Index: 5641623 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19