Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.4074. Min Act: -0.1700
Data Index: 7226625 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.3136. Min Act: -0.1700
Data Index: 2072638 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.3136. Min Act: -0.1700
Data Index: 7405043 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.3136. Min Act: -0.1700
Data Index: 3169818 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.3136. Min Act: -0.1700
Data Index: 898640 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2824. Min Act: -0.1700
Data Index: 6413065 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2824. Min Act: -0.1700
Data Index: 3645293 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2199. Min Act: -0.1700
Data Index: 7949468 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1191165 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 8127193 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 8138745 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 2537971 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 3582780 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 2658222 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 2891610 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1415248 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2199. Min Act: -0.1700
Data Index: 4642531 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2199. Min Act: -0.1700
Data Index: 4791145 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2199. Min Act: -0.1700
Data Index: 5667340 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4074. Min Range: -5.4074
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2731169 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19