Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0808. Min Range: -6.0808
Max Act: 6.0808. Min Act: -0.1700
Data Index: 1322944 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0808. Min Range: -6.0808
Max Act: 6.0183. Min Act: -0.1700
Data Index: 4785470 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.9246. Min Act: -0.1700
Data Index: 7084527 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.8933. Min Act: -0.1700
Data Index: 1046996 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.8621. Min Act: -0.1700
Data Index: 2085738 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7996. Min Act: -0.1700
Data Index: 597324 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.8621. Min Act: -0.1700
Data Index: 6168802 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.8308. Min Act: -0.1700
Data Index: 3768966 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7683. Min Act: -0.1700
Data Index: 5425525 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7683. Min Act: -0.1700
Data Index: 1306306 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7683. Min Act: -0.1700
Data Index: 8439939 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7371. Min Act: -0.1700
Data Index: 5290861 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7371. Min Act: -0.1700
Data Index: 3526061 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7683. Min Act: -0.1700
Data Index: 5805910 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1483606 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7058. Min Act: -0.1700
Data Index: 2910706 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6550029 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6702862 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.7058. Min Act: -0.1700
Data Index: 7578849 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0808. Min Range: -6.0808
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6478278 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19