Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 5005614 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 4967990 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 4136164 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.2683. Min Act: -0.1700
Data Index: 3778212 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.2058. Min Act: -0.1700
Data Index: 2516424 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.2058. Min Act: -0.1700
Data Index: 7211 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.2058. Min Act: -0.1700
Data Index: 6920285 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.1433. Min Act: -0.1700
Data Index: 6248555 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.1433. Min Act: -0.1700
Data Index: 6248064 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.0808. Min Act: -0.1700
Data Index: 3803683 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.0808. Min Act: -0.1700
Data Index: 6249499 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.0808. Min Act: -0.1700
Data Index: 3528814 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.0808. Min Act: -0.1700
Data Index: 7298152 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4558. Min Range: -8.4558
Max Act: 8.0808. Min Act: -0.1700
Data Index: 2872120 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.9558. Min Act: -0.1700
Data Index: 1878781 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.9558. Min Act: -0.1700
Data Index: 6971188 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.9558. Min Act: -0.1700
Data Index: 2155594 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.9558. Min Act: -0.1700
Data Index: 6536059 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.8933. Min Act: -0.1700
Data Index: 6393047 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4558. Min Range: -8.4558
Max Act: 7.8933. Min Act: -0.1700
Data Index: 5113166 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19