Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 408 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.7497. Min Act: -0.1700
Data Index: 5423537 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.6872. Min Act: -0.1700
Data Index: 2021134 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.5622. Min Act: -0.1700
Data Index: 6226721 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4997. Min Act: -0.1700
Data Index: 8414762 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1945101 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1111203 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4684. Min Act: -0.1700
Data Index: 1097548 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4684. Min Act: -0.1700
Data Index: 3826715 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4684. Min Act: -0.1700
Data Index: 3864023 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4372. Min Act: -0.1700
Data Index: 7756871 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.4059. Min Act: -0.1700
Data Index: 6414074 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3747. Min Act: -0.1700
Data Index: 2781419 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3747. Min Act: -0.1700
Data Index: 6859188 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3747. Min Act: -0.1700
Data Index: 1769394 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3747. Min Act: -0.1700
Data Index: 7488670 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3747. Min Act: -0.1700
Data Index: 5204298 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3434. Min Act: -0.1700
Data Index: 4750543 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3787014 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3648193 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7497. Min Range: -5.7497
Max Act: 5.3434. Min Act: -0.1700
Data Index: 7901517 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19