Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.6964. Min Act: -0.1700
Data Index: 145205 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.6651. Min Act: -0.1700
Data Index: 4245630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.6339. Min Act: -0.1700
Data Index: 6089486 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.5089. Min Act: -0.1700
Data Index: 2782820 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.4776. Min Act: -0.1700
Data Index: 1090434 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.4464. Min Act: -0.1700
Data Index: 374906 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.4151. Min Act: -0.1700
Data Index: 3054399 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.4151. Min Act: -0.1700
Data Index: 2254200 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.3526. Min Act: -0.1700
Data Index: 160321 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.3526. Min Act: -0.1700
Data Index: 3054380 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.3839. Min Act: -0.1700
Data Index: 2983650 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.3839. Min Act: -0.1700
Data Index: 7399301 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.3839. Min Act: -0.1700
Data Index: 5820160 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2901. Min Act: -0.1700
Data Index: 995046 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2901. Min Act: -0.1700
Data Index: 4291524 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2901. Min Act: -0.1700
Data Index: 6494175 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2901. Min Act: -0.1700
Data Index: 4481750 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2589. Min Act: -0.1700
Data Index: 181279 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.2589. Min Act: -0.1700
Data Index: 8466407 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6964. Min Range: -4.6964
Max Act: 4.1964. Min Act: -0.1700
Data Index: 6968350 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19