Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 7795138 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 5026706 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 5120299 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 657469 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 8419572 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 908196 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 7968718 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1766. Min Act: -0.1700
Data Index: 66191 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1453. Min Act: -0.1700
Data Index: 6964795 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1453. Min Act: -0.1700
Data Index: 5390357 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1453. Min Act: -0.1700
Data Index: 4142091 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 2847104 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 3683063 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 8449478 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 7960500 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 109831 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.1141. Min Act: -0.1700
Data Index: 5069143 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.0828. Min Act: -0.1700
Data Index: 3499734 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.0828. Min Act: -0.1700
Data Index: 6850092 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3016. Min Range: -5.3016
Max Act: 5.0516. Min Act: -0.1700
Data Index: 5013429 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19