Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7112. Min Range: -7.7112
Max Act: 7.7112. Min Act: -0.1700
Data Index: 7765544 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.8049. Min Act: -0.1700
Data Index: 5908813 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.7112. Min Act: -0.1700
Data Index: 2890274 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.6487. Min Act: -0.1700
Data Index: 6420079 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.6487. Min Act: -0.1700
Data Index: 3078613 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.6174. Min Act: -0.1700
Data Index: 1533825 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.5237. Min Act: -0.1700
Data Index: 2276247 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.4924. Min Act: -0.1700
Data Index: 5244689 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.4612. Min Act: -0.1700
Data Index: 3148020 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.4299. Min Act: -0.1700
Data Index: 2842317 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.4299. Min Act: -0.1700
Data Index: 6921459 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.4299. Min Act: -0.1700
Data Index: 1441851 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3674. Min Act: -0.1700
Data Index: 5035208 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3987. Min Act: -0.1700
Data Index: 3030579 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3674. Min Act: -0.1700
Data Index: 3309050 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3362. Min Act: -0.1700
Data Index: 7723056 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3049. Min Act: -0.1700
Data Index: 6951647 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3362. Min Act: -0.1700
Data Index: 1001807 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3362. Min Act: -0.1700
Data Index: 2245331 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7112. Min Range: -7.7112
Max Act: 6.3049. Min Act: -0.1700
Data Index: 607023 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19