Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0808. Min Range: -12.0808
Max Act: 12.0808. Min Act: -0.1700
Data Index: 7691809 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.7683. Min Act: -0.1700
Data Index: 2110100 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.3933. Min Act: -0.1700
Data Index: 310363 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.3933. Min Act: -0.1700
Data Index: 5684402 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.2683. Min Act: -0.1700
Data Index: 161385 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.2683. Min Act: -0.1700
Data Index: 2352386 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.3308. Min Act: -0.1700
Data Index: 968945 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.2058. Min Act: -0.1700
Data Index: 3520029 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.2058. Min Act: -0.1700
Data Index: 63038 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.1433. Min Act: -0.1700
Data Index: 6261152 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.1433. Min Act: -0.1700
Data Index: 6692339 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0808. Min Range: -12.0808
Max Act: 11.0808. Min Act: -0.1700
Data Index: 3612858 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 1709228 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 4237693 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 1631067 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 5328915 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 995167 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 7605289 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.9558. Min Act: -0.1700
Data Index: 161428 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0808. Min Range: -12.0808
Max Act: 10.8933. Min Act: -0.1700
Data Index: 7537990 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19