Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.5761. Min Act: -0.1700
Data Index: 4289947 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.5136. Min Act: -0.1700
Data Index: 2172503 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.5136. Min Act: -0.1700
Data Index: 3144181 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 4944795 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 4922975 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 6814280 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 7143056 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 7728743 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4823. Min Act: -0.1700
Data Index: 6175671 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4511. Min Act: -0.1700
Data Index: 3782123 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4511. Min Act: -0.1700
Data Index: 1138975 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4198. Min Act: -0.1700
Data Index: 4957254 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4198. Min Act: -0.1700
Data Index: 1209213 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4198. Min Act: -0.1700
Data Index: 7780638 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4198. Min Act: -0.1700
Data Index: 700421 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.3886. Min Act: -0.1700
Data Index: 4169415 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.4198. Min Act: -0.1700
Data Index: 3705825 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.3886. Min Act: -0.1700
Data Index: 5614932 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.3886. Min Act: -0.1698
Data Index: 3293195 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5761. Min Range: -5.5761
Max Act: 5.3886. Min Act: -0.1700
Data Index: 6287260 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19