Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0693. Min Act: -0.1700
Data Index: 866742 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9130. Min Act: -0.1700
Data Index: 6230001 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8818. Min Act: -0.1700
Data Index: 212703 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8818. Min Act: -0.1700
Data Index: 683849 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9130. Min Act: -0.1700
Data Index: 725037 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8505. Min Act: -0.1700
Data Index: 6984652 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8193. Min Act: -0.1700
Data Index: 3925460 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8193. Min Act: -0.1700
Data Index: 2138509 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8193. Min Act: -0.1700
Data Index: 3188747 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.7568. Min Act: -0.1700
Data Index: 136164 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.7568. Min Act: -0.1700
Data Index: 5772592 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.7255. Min Act: -0.1700
Data Index: 7123058 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.7568. Min Act: -0.1700
Data Index: 1898195 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6943. Min Act: -0.1700
Data Index: 1471465 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6943. Min Act: -0.1700
Data Index: 1926138 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6943. Min Act: -0.1700
Data Index: 2366361 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6943. Min Act: -0.1700
Data Index: 5048807 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6943. Min Act: -0.1700
Data Index: 2574650 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6630. Min Act: -0.1700
Data Index: 297920 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.6630. Min Act: -0.1700
Data Index: 3932473 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19