Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.2759. Min Act: -0.1700
Data Index: 1900739 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.2447. Min Act: -0.1700
Data Index: 4520168 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.2759. Min Act: -0.1700
Data Index: 5352191 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.2134. Min Act: -0.1700
Data Index: 1867414 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.1822. Min Act: -0.1700
Data Index: 4817837 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6136341 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.1509. Min Act: -0.1700
Data Index: 6880690 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0884. Min Act: -0.1700
Data Index: 8061197 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.1197. Min Act: -0.1700
Data Index: 3044293 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1920873 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0572. Min Act: -0.1700
Data Index: 3154638 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0259. Min Act: -0.1700
Data Index: 882101 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0259. Min Act: -0.1700
Data Index: 6709241 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 8582204 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 6348789 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2759. Min Range: -5.2759
Max Act: 5.0259. Min Act: -0.1700
Data Index: 902002 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 3007874 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 3788728 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 270260 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2759. Min Range: -5.2759
Max Act: 4.9947. Min Act: -0.1700
Data Index: 5030269 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19