Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1146 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.7101. Min Act: -0.1700
Data Index: 2833534 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.5226. Min Act: -0.1700
Data Index: 8388859 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.4601. Min Act: -0.1700
Data Index: 4609914 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.2726. Min Act: -0.1700
Data Index: 3802020 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.2101. Min Act: -0.1700
Data Index: 6413743 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.2101. Min Act: -0.1700
Data Index: 8514649 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.1788. Min Act: -0.1700
Data Index: 6368090 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.1476. Min Act: -0.1700
Data Index: 4789185 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.1476. Min Act: -0.1700
Data Index: 7598183 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.1788. Min Act: -0.1700
Data Index: 2052267 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.0851. Min Act: -0.1700
Data Index: 3111780 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.1163. Min Act: -0.1700
Data Index: 321452 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7101. Min Range: -7.7101
Max Act: 7.0851. Min Act: -0.1700
Data Index: 2824852 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9601. Min Act: -0.1700
Data Index: 6546856 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9913. Min Act: -0.1700
Data Index: 6443122 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9913. Min Act: -0.1700
Data Index: 6305249 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9913. Min Act: -0.1700
Data Index: 1523066 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9601. Min Act: -0.1700
Data Index: 7982418 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9601. Min Act: -0.1700
Data Index: 6572211 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7101. Min Range: -7.7101
Max Act: 6.9288. Min Act: -0.1700
Data Index: 459582 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19