Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.4362. Min Act: -0.1700
Data Index: 1174617 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.2799. Min Act: -0.1700
Data Index: 6913151 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.2487. Min Act: -0.1700
Data Index: 4511 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.2174. Min Act: -0.1700
Data Index: 8734868 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.2174. Min Act: -0.1700
Data Index: 473940 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.0924. Min Act: -0.1700
Data Index: 5594562 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.0612. Min Act: -0.1700
Data Index: 5214244 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.0612. Min Act: -0.1700
Data Index: 1668474 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4362. Min Range: -7.4362
Max Act: 7.0299. Min Act: -0.1700
Data Index: 570119 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9987. Min Act: -0.1700
Data Index: 6855725 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9049. Min Act: -0.1700
Data Index: 7860620 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9362. Min Act: -0.1700
Data Index: 2054574 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9049. Min Act: -0.1700
Data Index: 3071718 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9049. Min Act: -0.1700
Data Index: 2016462 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9049. Min Act: -0.1700
Data Index: 6885582 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9362. Min Act: -0.1700
Data Index: 3527283 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.8737. Min Act: -0.1700
Data Index: 5125623 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.9049. Min Act: -0.1700
Data Index: 4402167 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.8737. Min Act: -0.1700
Data Index: 3549867 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4362. Min Range: -7.4362
Max Act: 6.8424. Min Act: -0.1700
Data Index: 1746188 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19